Beispiele für die Verwendung von Select AI
Entdecken Sie die Integration von Select AI von Oracle mit verschiedenen unterstützten KI-Providern, um SQL aus Eingabeaufforderungen in natürlicher Sprache zu generieren, auszuführen und zu erklären oder mit dem LLM zu chatten.
- Beispiel: AI-Aktionen auswählen
Diese Beispiele veranschaulichen allgemeine AI-Aktionen zum Auswählen. - Beispiel: KI mit OCI Generative AI auswählen
Diese Beispiele zeigen, wie Sie mit Ihrem OCI-API-Schlüssel oder Resource Principal auf OCI Generative AI zugreifen, ein KI-Profil erstellen sowie SQL aus Eingabeaufforderungen in natürlicher Sprache generieren, ausführen und erläutern oder mit den OCI Generative AI LLMs chatten können. - Beispiel: AI mit OpenAI auswählen
In diesem Beispiel wird gezeigt, wie Sie mit OpenAI SQL-Anweisungen aus Eingabeaufforderungen in natürlicher Sprache generieren können. - Beispiel: AI mit Cohere auswählen
Dieses Beispiel zeigt, wie Sie mit Cohere SQL-Anweisungen aus Eingabeaufforderungen in natürlicher Sprache generieren können. - Beispiel: AI mit Azure-Service OpenAI auswählen
Die folgenden Beispiele zeigen, wie Sie den Zugriff auf den Azure-Service OpenAI mit Ihrem API-Schlüssel aktivieren oder den Azure-Service-Principal OpenAI verwenden, ein AI-Profil erstellen und SQL aus Eingabeaufforderungen in natürlicher Sprache generieren können. - Beispiel: AI mit Google auswählen
Dieses Beispiel zeigt, wie Sie mit Google SQL aus Eingabeaufforderungen in natürlicher Sprache generieren, ausführen und erklären oder mit Google Gemini LLM chatten können. - Beispiel: AI mit Anthropic auswählen
Dieses Beispiel zeigt, wie Sie mit Anthropic SQL aus Eingabeaufforderungen in natürlicher Sprache generieren, ausführen und erklären oder mit Anthropic Claude LLM chatten können. - Beispiel: AI mit umarmender Fläche auswählen
Dieses Beispiel zeigt, wie Sie mit Hugging Face SQL aus Eingabeaufforderungen in natürlicher Sprache oder Chat mit dem umarmenden Face-LLM generieren, ausführen und erklären können. - Beispiel: Unterhaltungen in "AI auswählen" aktivieren
Dieses Beispiel veranschaulicht das Aktivieren von Unterhaltungen in "AI auswählen". - Beispiel: Select AI mit RAG einrichten und verwenden
In diesem Beispiel werden Sie durch das Einrichten von Zugangsdaten, das Konfigurieren des Netzwerkzugriffs und das Erstellen eines Vektorindex für die Integration von Cloud-Services des OCI Generative AI-Vektorspeichers mit OpenAI mit Oracle Autonomous Database geführt. - Beispiel: AI mit datenbankinternen Transformer-Modellen auswählen
Dieses Beispiel zeigt, wie Sie ein vortrainiertes Transformer-Modell, das im Oracle-Objektspeicher gespeichert ist, in Ihre Oracle Database 23ai-Instanz importieren und dann das importierte datenbankinterne Modell im AI-Profil "Auswählen" verwenden können, um Vektoreinbettungen für Dokumentblöcke und Benutzer-Prompts zu generieren. - Beispiel: SQL-Abfragegenerierung verbessern
Diese Beispiele zeigen, wie Kommentare, Anmerkungen, Fremdschlüssel und referenzielle Integritäts-Constraints in Datenbanktabellen und -spalten die Generierung von SQL-Abfragen aus Eingabeaufforderungen in natürlicher Sprache verbessern können. - Beispiel: Synthetische Daten generieren
In diesem Beispiel wird erläutert, wie Sie synthetische Daten generieren können, die den Merkmalen und der Verteilung echter Daten nachahmen. - Beispiel: Datenzugriff aktivieren oder deaktivieren
Dieses Beispiel veranschaulicht, wie Administratoren den Datenzugriff steuern und verhindern können, dass Select AI tatsächliche Schematabellen an LLM sendet. - Beispiel: Tabellenzugriff in AI-Profil einschränken
Dieses Beispiel zeigt, wie Sie den Tabellenzugriff einschränken und LLM anweisen, nur die inobject_listdes AI-Profils angegebenen Tabellen zu verwenden. - Beispiel: Groß-/Kleinschreibung für Spalten angeben
Dieses Beispiel zeigt, wie Sie die Groß-/Kleinschreibung für Spalten im AI-Profil festlegen können.
Übergeordnetes Thema: Select AI für Natural Language Interaction mit Ihrer Datenbank verwenden
Beispiel: AI-Aktionen auswählen
Diese Beispiele veranschaulichen gängige Select AI-Aktionen.
Das folgende Beispiel zeigt Aktionen wie runsql (Standard), showsql, narrate, chat und explainsql, die Sie mit SELECT AI ausführen können. In diesen Beispielen wird das Schema sh mit AI-Provider und Profilattributen verwendet, die in der Funktion DBMS_CLOUD_AI.CREATE_PROFILE festgelegt sind.
SQL> select ai how many customers exist;
CUSTOMER_COUNT
--------------
55500
SQL> select ai showsql how many customers exist;
RESPONSE
----------------------------------------------------
SELECT COUNT(*) AS total_customers
FROM SH.CUSTOMERS
SQL> select ai narrate how many customers exist;
RESPONSE
------------------------------------------------------
There are a total of 55,500 customers in the database.
SQL> select ai chat how many customers exist;
RESPONSE
--------------------------------------------------------------------------------
It is impossible to determine the exact number of customers that exist as it con
stantly changes due to various factors such as population growth, new businesses
, and customer turnover. Additionally, the term "customer" can refer to individu
als, businesses, or organizations, making it difficult to provide a specific num
ber.
SQL> select ai explainsql how many customers in San Francisco are married;
RESPONSE
--------------------------------------------------------------------------------
SELECT COUNT(*) AS customer_count
FROM SH.CUSTOMERS AS c
WHERE c.CUST_STATE_PROVINCE = 'San Francisco' AND c.CUST_MARITAL_STATUS = 'Married';
Explanation:
- We use the 'SH' table alias for the 'CUSTOMERS' table for better readability.
- The query uses the 'COUNT(*)' function to count the number of rows that match the given conditions.
- The 'WHERE' clause is used to filter the results:
- 'c.CUST_STATE_PROVINCE = 'San Francisco'' filters customers who have 'San Francisco' as their state or province.
- 'c.CUST_MARITAL_STATUS = 'Married'' filters customers who have 'Married' as their marital status.
The result of this query will give you the count of customers in San Francisco who are married, using the column alias 'customer_count' for the result.
Remember to adjust the table and column names based on your actual schema if they differ from the example.
Feel free to ask if you have more questions related to SQL or database in general.Übergeordnetes Thema: Beispiele für die Verwendung von Select AI
Beispiel: AI mit OCI Generative AI auswählen
Diese Beispiele zeigen, wie Sie mit Ihrem OCI-API-Schlüssel oder Resource Principal auf OCI Generative AI zugreifen, ein KI-Profil erstellen und SQL aus Eingabeaufforderungen in natürlicher Sprache generieren, ausführen und erläutern oder mit den OCI Generative AI LLMs chatten können.
Hinweis
Wenn Sie den Parameter
Wenn Sie den Parameter
model_name nicht angeben, verwendet OCI Generative AI das Standardmodell gemäß der Tabelle unter AI-Provider und LLMs auswählen. Weitere Informationen zu den Parametern finden Sie unter Profilattribute.
-- Create Credential with OCI API key
--
BEGIN
DBMS_CLOUD.CREATE_CREDENTIAL(
credential_name => 'GENAI_CRED',
user_ocid => 'ocid1.user.oc1..aaaa...',
tenancy_ocid => 'ocid1.tenancy.oc1..aaaa...',
private_key => '<your_api_key>',
fingerprint => '<your_fingerprint>'
);
END;
/
--
-- Create AI profile
--
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name =>'GENAI',
attributes =>'{"provider": "oci",
"credential_name": "GENAI_CRED",
"object_list": [{"owner": "SH", "name": "customers"},
{"owner": "SH", "name": "countries"},
{"owner": "SH", "name": "supplementary_demographics"},
{"owner": "SH", "name": "profits"},
{"owner": "SH", "name": "promotions"},
{"owner": "SH", "name": "products"}]
}');
END;
/
PL/SQL procedure successfully completed.
--
-- Enable AI profile in current session
--
EXEC DBMS_CLOUD_AI.SET_PROFILE('GENAI');
PL/SQL procedure successfully completed.
--
-- Get Profile in current session
--
SELECT DBMS_CLOUD_AI.get_profile() from dual;
DBMS_CLOUD_AI.GET_PROFILE()
--------------------------------------------------------------------------------
"GENAI"
--
-- Use AI
--
SQL> select ai how many customers exist;
Number of Customers
-------------------
55500
SQL> select ai how many customers in San Francisco are married;
COUNT(DISTINCTC."CUST_ID")
--------------------------
28
SQL> select ai showsql how many customers in San Francisco are married;
RESPONSE
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
SELECT COUNT(DISTINCT c."CUST_ID")
FROM "SH"."CUSTOMERS" c
JOIN "SH"."COUNTRIES" co ON c."COUNTRY_ID" = co."COUNTRY_ID"
WHERE c."CUST_CITY" = 'San Francisco' AND c."CUST_MARITAL_STATUS" = 'married'
SQL> select ai explainsql how many customers in San Francisco are married;
RESPONSE
Here is the Oracle SQL query to find the number of customers in San Francisco who are married:
```
SELECT COUNT(*)
FROM "SH"."CUSTOMERS" c
WHERE c."CUST_CITY" = 'San Francisco'
AND c."CUST_MARITAL_STATUS" = 'Married';
```
Explanation:
* We use the `COUNT(*)` aggregate function to count the number of rows that match the conditions.
* We specify the table alias `c` for the `"SH"."CUSTOMERS"` table to make the query more readable.
* We use the `WHERE` clause to filter the rows based on two conditions:
+ `c."CUST_CITY" = 'San Francisco'`: We filter the rows where the customer's city is San Francisco.
+ `c."CUST_MARITAL_STATUS" = 'Married'`: We filter the rows where the customer's marital status is Married.
* The double quotes around the table and column names are used to make the query case-sensitive, as required in Oracle SQL.
Note: The column names and table names are assumed to be case-sensitive, so we enclose them in double quotes. If the column names and table names are not case-sensitive, you can remove the double quotes.
Collapse
This snippet was truncated for display; see it in full
SQL> select ai narrate how many customers in San Francisco are married;
RESPONSE
--------------------------------------------------------
There are 28 customers in San Francisco who are married.
SQL> select ai chat what is Autonomous Database;
RESPONSE
An Autonomous Database is a type of database that uses artificial intelligence (AI) and machine learning (ML) to automate many of the administrative and maintenance tasks typically performed by a database administrator (DBA). This allows the database to manage itself, without human intervention, to a large extent.
Autonomous databases are designed to be self-driving, self-securing, and self-repairing, which means they can:
1. **Automate administrative tasks**: Such as provisioning, patching, upgrading, and tuning, which frees up DBAs to focus on higher-level tasks.
2. **Optimize performance**: By automatically adjusting parameters, indexing, and caching to ensure optimal performance and efficiency.
3. **Detect and respond to security threats**: By using AI-powered security tools to identify and respond to potential security threats in real-time.
4. **Heal itself**: By automatically detecting and repairing errors, corruption, or other issues that may arise.
5. **Scale up or down**: To match changing workload demands, without the need for manual intervention.
The benefits of Autonomous Databases include:
1. **Increased efficiency**: By automating routine tasks, DBAs can focus on more strategic activities.
2. **Improved performance**: Autonomous databases can optimize performance in real-time, leading to faster query response times and better overall system performance.
3. **Enhanced security**: AI-powered security tools can detect and respond to threats more quickly and effectively than human administrators.
4. **Reduced costs**: By minimizing the need for manual intervention, Autonomous Databases can help reduce labor costs and improve resource utilization.
5. **Improved reliability**: Autonomous Databases can detect and repair errors more quickly, reducing downtime and improving overall system reliability.
Oracle Autonomous Database is a popular example of an Autonomous Database, which was introduced in 2018. Other vendors, such as Amazon, Microsoft, and Google, also offer Autonomous Database services as part of their cloud offerings.
In summary, Autonomous Databases are designed to be self-managing, self-optimizing, and self-healing, which can lead to improved performance, security, and efficiency, while reducing costs and administrative burdens.
--
--Drop the profile
--
EXEC DBMS_CLOUD_AI.DROP_PROFILE('GENAI');
PL/SQL procedure successfully completed.Beispiel: AI mit OCI Generative AI Resource Principal auswählen
Um den Resource Principal mit OCI Generative AI zu verwenden, muss der Oracle Cloud Infrastructure-Mandantenadministrator einer dynamischen Gruppe Zugriff auf generative KI-Ressourcen erteilen. Siehe Voraussetzungen für die Verwendung von Resource Principal mit Autonomous Database ausführen, um Zugriff auf eine dynamische Gruppe zu erteilen.
Legen Sie die erforderlichen Policys fest, um Zugriff auf alle generativen KI-Ressourcen zu erhalten. Weitere Informationen zu generativen KI-Policys finden Sie unter Zugriff auf generative KI erhalten.
-
Um Zugriff auf alle generative KI-Ressourcen im gesamten Mandanten zu erhalten, verwenden Sie die folgende Policy:
allow group <your-group-name> to manage generative-ai-family in tenancy -
Um Zugriff auf alle generative KI-Ressourcen in Ihrem Compartment zu erhalten, verwenden Sie die folgende Policy:
allow group <your-group-name> to manage generative-ai-family in compartment <your-compartment-name>
Melden Sie sich als Administrator an, und aktivieren Sie den OCI-Resource Principal. Informationen zur Konfiguration der Parameter finden Sie unter Prozedur ENABLE_PRINCIPAL_AUTH.
Hinweis
OCI Generative AI verwendet
OCI Generative AI verwendet
meta.llama-3-70b-instruct als Standardmodell, wenn Sie model nicht angeben. Weitere Informationen zu den Parametern finden Sie unter Profilattribute.
-- Connect as Administrator user and enable OCI resource principal.
BEGIN
DBMS_CLOUD_ADMIN.ENABLE_PRINCIPAL_AUTH(provider => 'OCI');
END;
/
--
-- Create AI profile
--
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name =>'GENAI',
attributes =>'{"provider": "oci",
"credential_name": "OCI$RESOURCE_PRINCIPAL",
"object_list": [{"owner": "SH", "name": "customers"},
{"owner": "SH", "name": "countries"},
{"owner": "SH", "name": "supplementary_demographics"},
{"owner": "SH", "name": "profits"},
{"owner": "SH", "name": "promotions"},
{"owner": "SH", "name": "products"}]
}');
END;
/
PL/SQL procedure successfully completed.
--
-- Enable AI profile in current session
--
EXEC DBMS_CLOUD_AI.SET_PROFILE('GENAI');
PL/SQL procedure successfully completed.
--
-- Get Profile in current session
--
SELECT DBMS_CLOUD_AI.get_profile() from dual;
DBMS_CLOUD_AI.GET_PROFILE()
--------------------------------------------------------------------------------
"GENAI"
--
-- Use AI
--
SQL> select ai how many customers exist;
Number of Customers
-------------------
55500
SQL> select ai how many customers in San Francisco are married;
COUNT(DISTINCTC."CUST_ID")
--------------------------
28
SQL> select ai showsql how many customers in San Francisco are married;
RESPONSE
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
SELECT COUNT(DISTINCT c."CUST_ID")
FROM "SH"."CUSTOMERS" c
JOIN "SH"."COUNTRIES" co ON c."COUNTRY_ID" = co."COUNTRY_ID"
WHERE c."CUST_CITY" = 'San Francisco' AND c."CUST_MARITAL_STATUS" = 'married'
SQL> select ai explainsql how many customers in San Francisco are married;
RESPONSE
Here is the Oracle SQL query to find the number of customers in San Francisco who are married:
```
SELECT COUNT(*)
FROM "SH"."CUSTOMERS" c
WHERE c."CUST_CITY" = 'San Francisco'
AND c."CUST_MARITAL_STATUS" = 'Married';
```
Explanation:
* We use the `COUNT(*)` aggregate function to count the number of rows that match the conditions.
* We specify the table alias `c` for the `"SH"."CUSTOMERS"` table to make the query more readable.
* We use the `WHERE` clause to filter the rows based on two conditions:
+ `c."CUST_CITY" = 'San Francisco'`: We filter the rows where the customer's city is San Francisco.
+ `c."CUST_MARITAL_STATUS" = 'Married'`: We filter the rows where the customer's marital status is Married.
* The double quotes around the table and column names are used to make the query case-sensitive, as required in Oracle SQL.
Note: The column names and table names are assumed to be case-sensitive, so we enclose them in double quotes. If the column names and table names are not case-sensitive, you can remove the double quotes.
Collapse
This snippet was truncated for display; see it in full
SQL> select ai narrate how many customers in San Francisco are married;
RESPONSE
--------------------------------------------------------
There are 28 customers in San Francisco who are married.
SQL> select ai chat what is Autonomous Database;
RESPONSE
An Autonomous Database is a type of database that uses artificial intelligence (AI) and machine learning (ML) to automate many of the administrative and maintenance tasks typically performed by a database administrator (DBA). This allows the database to manage itself, without human intervention, to a large extent.
Autonomous databases are designed to be self-driving, self-securing, and self-repairing, which means they can:
1. **Automate administrative tasks**: Such as provisioning, patching, upgrading, and tuning, which frees up DBAs to focus on higher-level tasks.
2. **Optimize performance**: By automatically adjusting parameters, indexing, and caching to ensure optimal performance and efficiency.
3. **Detect and respond to security threats**: By using AI-powered security tools to identify and respond to potential security threats in real-time.
4. **Heal itself**: By automatically detecting and repairing errors, corruption, or other issues that may arise.
5. **Scale up or down**: To match changing workload demands, without the need for manual intervention.
The benefits of Autonomous Databases include:
1. **Increased efficiency**: By automating routine tasks, DBAs can focus on more strategic activities.
2. **Improved performance**: Autonomous databases can optimize performance in real-time, leading to faster query response times and better overall system performance.
3. **Enhanced security**: AI-powered security tools can detect and respond to threats more quickly and effectively than human administrators.
4. **Reduced costs**: By minimizing the need for manual intervention, Autonomous Databases can help reduce labor costs and improve resource utilization.
5. **Improved reliability**: Autonomous Databases can detect and repair errors more quickly, reducing downtime and improving overall system reliability.
Oracle Autonomous Database is a popular example of an Autonomous Database, which was introduced in 2018. Other vendors, such as Amazon, Microsoft, and Google, also offer Autonomous Database services as part of their cloud offerings.
In summary, Autonomous Databases are designed to be self-managing, self-optimizing, and self-healing, which can lead to improved performance, security, and efficiency, while reducing costs and administrative burdens.
--
--Drop the profile
--
EXEC DBMS_CLOUD_AI.DROP_PROFILE('GENAI');
PL/SQL procedure successfully completed.Beispiel: Andere Region für OCI Generative AI-Profil angeben
In diesem Beispiel wird eine von OCI Generative AI unterstützte Region in Ihrem Profil angegeben. Siehe Regionen mit generativer KI.
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name => 'GENAI',
attributes =>'{"provider": "oci",
"object_list": [
{"owner": "SH", "name": "customers"},
{"owner": "SH", "name": "countries"},
{"owner": "SH", "name": "supplementary_demographics"},
{"owner": "SH", "name": "profits"},
{"owner": "SH", "name": "promotions"},
{"owner": "SH", "name": "products"}
]
"region":"eu-frankfurt-1",
"model": "meta.llama-3.3-70b-instruct",
"credential_name": "GENAI_CRED",
"oci_compartment_id": "ocid1.compartment.oc1..."}');
END;
/Beispiel: AI mit OCI Generative AI mit LLAMA-Modell auswählen
In diesem Beispiel wird das Feature chat von OCI Generative AI dargestellt. Es hebt die Fähigkeiten des Modells durch zwei Eingabeaufforderungen hervor: Analyse von Kundenkommentaren, um ihre Stimmung zu erfassen und einen einleitenden Absatz zum Klettern zu generieren.
BEGIN
DBMS_CLOUD.CREATE_CREDENTIAL(
credential_name => 'GENAI_CRED',
user_ocid => 'ocid1.user.oc1..aaa',
tenancy_ocid => 'ocid1.tenancy.oc1..aaa',
private_key => '<your_api_key>',
fingerprint => '<your_fingerprint>'
);
END;
/
PL/SQL procedure successfully completed.
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name => 'GENAI',
attributes =>'{"provider": "oci",
"object_list": [
{"owner": "SH", "name": "customers"},
{"owner": "SH", "name": "countries"},
{"owner": "SH", "name": "supplementary_demographics"},
{"owner": "SH", "name": "profits"},
{"owner": "SH", "name": "promotions"},
{"owner": "SH", "name": "products"}
]
"model": "meta.llama-3.3-70b-instruct",
"oci_apiformat":"GENERIC",
"credential_name": "GENAI_CRED",
"oci_compartment_id": "ocid1.compartment.oc1..."}');
END;
/
PL/SQL procedure successfully completed.
--
--Set profile
--
EXEC DBMS_CLOUD_AI.SET_PROFILE('GENAI');
PL/SQL procedure successfully completed.
SQL> set linesize 150
SQL> SELECT AI chat what is the sentiment of this comment I am not going to waste my time filling up this three page form. Lousy idea;
SQL>
RESPONSE
------------------------------------------------------------------------------------------------------------------------------------------------------
The sentiment of this comment is strongly negative. The user is expressing frustration and annoyance with the idea of filling out a three-page form, an
d is explicitly stating that they consider it a "lousy idea". The use of the phrase "waste my time" also implies that they feel the task is unnecessary
and unproductive. The tone is dismissive and critical.
SQL> SELECT AI chat Write an enthusiastic introductory paragraph on how to get started with rock climbing with Athletes as the target audience;
RESPONSE
------------------------------------------------------------------------------------------------------------------------------------------------------
Rock climbing is an exhilarating and challenging sport that's perfect for athletes looking to push their limits and test their strength, endurance,
and mental toughness. Whether you're a seasoned athlete or just starting out, rock climbing offers a unique and rewarding experience that will have
you hooked from the very first climb. With its combination of physical and mental challenges, rock climbing is a great way to build strength, improve
flexibility, and develop problem-solving skills. Plus, with the supportive community of climbers and the breathtaking views from the top of the climb,
you'll be hooked from the very first climb. So, if you're ready to take on a new challenge and experience the thrill of adventure, then it's time to
get started with rock climbing!OCI Generative AI mit dem Standardmodell verwenden
Im folgenden Beispiel wird das standardmäßige OCI Generative AI-Chatmodell verwendet. Wenn Sie den Parameter model_name nicht angeben, verwendet OCI Generative AI das Standardmodell gemäß der Tabelle unter AI-Provider und LLMs auswählen.
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name => 'OCI_DEFAULT',
attributes => '{"provider": "oci",
"credential_name": "OCI_CRED",
"object_list": [{"owner": "ADB_USER"}]
}');
END;
/OCI Generative AI mit Chatmodell verwenden
Im folgenden Beispiel wird cohere.command-r-plus-08-2024 als OCI Generative AI-Chatmodell verwendet.
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name => 'OCI_COHERE_COMMAND_R_PLUS',
attributes => '{"provider": "oci",
"credential_name": "OCI_CRED",
"object_list": [{"owner": "ADB_USER"}],
"model": "cohere.command-r-plus-08-2024"
}');
END;
/OCI Generative AI mit Chatmodell-Endpunkt-ID verwenden
Das folgende Beispiel zeigt, wie Sie die Endpunkt-ID des OCI Generative AI-Chatmodells anstelle von model angeben. Wenn Sie die Endpunkt-ID des Meta-Llama-Chatmodells verwenden, geben Sie oci_apiformat als GENERIC an.
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name => 'OCI_CHAT_ENDPOINT',
attributes => '{"provider": "oci",
"credential_name": "OCI_CRED",
"object_list": [{"owner": "ADB_USER"}],
"oci_endpoint_id": "<endpoint_id>",
"oci_apiformat": "GENERIC"
}');
END;
/OCI Generative AI mit Chatmodell-OCID verwenden
In diesem Beispiel wird gezeigt, wie Sie die Endpunkt-ID des OCI Generative AI Cohere Chatmodells anstelle von model angeben. Wenn Sie die Endpunkt-ID des Meta-Llama-Chatmodells verwenden, geben Sie oci_apiformat als GENERIC an.
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name => 'OCI_CHAT_OCID',
attributes => '{"provider": "oci",
"credential_name": "OCI_CRED",
"object_list": [{"owner": "ADB_USER"}],
"model": "<model_ocid>",
"oci_apiformat": "COHERE"
}');
END;
/Übergeordnetes Thema: Beispiele für die Verwendung von Select AI
Beispiel: Wählen Sie AI mit OpenAI aus
Dieses Beispiel zeigt, wie Sie mit OpenAI SQL-Anweisungen aus Eingabeaufforderungen in natürlicher Sprache generieren können.
Hinweis
Nur ein DBA kann
Nur ein DBA kann
EXECUTE-Berechtigungen und die Netzwerk-ACL-Prozedur ausführen.
--Grants EXECUTE privilege to ADB_USER
--
SQL> grant execute on DBMS_CLOUD_AI to ADB_USER;
-- Grant Network ACL for OpenAI endpoint
--
SQL> BEGIN
DBMS_NETWORK_ACL_ADMIN.APPEND_HOST_ACE(
host => 'api.openai.com',
ace => xs$ace_type(privilege_list => xs$name_list('http'),
principal_name => 'ADB_USER',
principal_type => xs_acl.ptype_db)
);
END;
/
PL/SQL procedure successfully completed.
--
-- Create Credential for AI provider
--
EXEC
DBMS_CLOUD.CREATE_CREDENTIAL(
CREDENTIAL_NAME => 'OPENAI_CRED',
username => 'OPENAI',
password => '<your_api_token>');
PL/SQL procedure successfully completed.
--
-- Create AI profile
--
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name => 'OPENAI',
attributes =>'{"provider": "openai",
"credential_name": "OPENAI_CRED",
"object_list": [{"owner": "SH", "name": "customers"},
{"owner": "SH", "name": "countries"},
{"owner": "SH", "name": "supplementary_demographics"},
{"owner": "SH", "name": "profits"},
{"owner": "SH", "name": "promotions"},
{"owner": "SH", "name": "products"}],
"conversation": "true"
}');
END;
/
PL/SQL procedure successfully completed.
--
-- Enable AI profile in current session
--
SQL> EXEC DBMS_CLOUD_AI.SET_PROFILE('OPENAI');
PL/SQL procedure successfully completed.
--
-- Get Profile in current session
--
SQL> SELECT DBMS_CLOUD_AI.get_profile() from dual;
DBMS_CLOUD_AI.GET_PROFILE()
--------------------------------------------------------------------------------
"OPENAI"
--
-- Use AI
--
SQL> select ai how many customers exist;
CUSTOMER_COUNT
--------------
55500
SQL> select ai how many customers in San Francisco are married;
MARRIED_CUSTOMERS
-----------------
18
SQL> select ai showsql how many customers in San Francisco are married;
RESPONSE
--------------------------------------------------------------------------------
SELECT COUNT(*) AS married_customers_count
FROM SH.CUSTOMERS c
WHERE c.CUST_CITY = 'San Francisco'
AND c.CUST_MARITAL_STATUS = 'Married'
SQL> select ai explainsql how many customers in San Francisco are married;
RESPONSE
--------------------------------------------------------------------------------
SELECT COUNT(*) AS customer_count
FROM SH.CUSTOMERS AS c
WHERE c.CUST_STATE_PROVINCE = 'San Francisco' AND c.CUST_MARITAL_STATUS = 'Married';
Explanation:
- We use the 'SH' table alias for the 'CUSTOMERS' table for better readability.
- The query uses the 'COUNT(*)' function to count the number of rows that match the given conditions.
- The 'WHERE' clause is used to filter the results:
- 'c.CUST_STATE_PROVINCE = 'San Francisco'' filters customers who have 'San Francisco' as their state or province.
- 'c.CUST_MARITAL_STATUS = 'Married'' filters customers who have 'Married' as their marital status.
The result of this query will give you the count of customers in San Francisco who are married, using the column alias 'customer_count' for the result.
Remember to adjust the table and column names based on your actual schema if they differ from the example.
Feel free to ask if you have more questions related to SQL or database in general.
SQL> select ai narrate what are the top 3 customers in San Francisco;
RESPONSE
--------------------------------------------------------------------------------
The top 3 customers in San Francisco are:
1. Hector Colven - Total amount sold: $52,025.99
2. Milburn Klemm - Total amount sold: $50,842.28
3. Gavin Xie - Total amount sold: $48,677.18
SQL> select ai chat what is Autonomous Database;
RESPONSE
--------------------------------------------------------------------------------
Autonomous Database is a cloud-based database service provided by Oracle. It is designed to automate many of the routine tasks involved in managing a database,
such as patching, tuning, and backups. Autonomous Database uses machine learning and automation to optimize performance, security, and availability, allowing
users to focus on their applications and data rather than database administration tasks. It offers both Autonomous Transaction Processing (ATP) for
transactional workloads and Autonomous Data Warehouse (ADW) for analytical workloads. Autonomous Database provides high performance, scalability, and
reliability, making it an ideal choice for modern cloud-based applications.
SQL> EXEC DBMS_CLOUD_AI.DROP_PROFILE('OPENAI');
PL/SQL procedure successfully completed.Das folgende Beispiel zeigt, wie Sie ein anderes Modell in Ihrem AI-Profil angeben:
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name => 'OPENAI',
attributes =>'{"provider": "openai",
"credential_name": "OPENAI_CRED",
"model": "gpt-3.5-turbo",
"object_list": [{"owner": "SH", "name": "customers"},
{"owner": "SH", "name": "countries"},
{"owner": "SH", "name": "supplementary_demographics"},
{"owner": "SH", "name": "profits"},
{"owner": "SH", "name": "promotions"},
{"owner": "SH", "name": "products"}],
"conversation": "true"
}');
END;
/ Übergeordnetes Thema: Beispiele für die Verwendung von Select AI
Beispiel: AI mit Cohere auswählen
Dieses Beispiel zeigt, wie Sie mit Cohere SQL-Anweisungen aus Eingabeaufforderungen in natürlicher Sprache generieren können.
Hinweis
Nur ein DBA kann
Nur ein DBA kann
EXECUTE-Berechtigungen und die Netzwerk-ACL-Prozedur ausführen.
--Grants EXECUTE privilege to ADB_USER
--
SQL>GRANT execute on DBMS_CLOUD_AI to ADB_USER;
--
-- Create Credential for AI provider
--
EXEC
DBMS_CLOUD.CREATE_CREDENTIAL(
CREDENTIAL_NAME => 'COHERE_CRED',
username => 'COHERE',
password => 'your_api_token');
PL/SQL procedure successfully completed.
--
-- Grant Network ACL for Cohere endpoint
--
SQL> BEGIN
DBMS_NETWORK_ACL_ADMIN.APPEND_HOST_ACE(
host => 'api.cohere.ai',
ace => xs$ace_type(privilege_list => xs$name_list('http'),
principal_name => 'ADB_USER',
principal_type => xs_acl.ptype_db)
);
END;
/
/
PL/SQL procedure successfully completed.
--
-- Create AI profile
--
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name => 'COHERE',
attributes =>'{"provider": "cohere",
"credential_name": "COHERE_CRED",
"object_list": [{"owner": "SH", "name": "customers"},
{"owner": "SH", "name": "sales"},
{"owner": "SH", "name": "products"},
{"owner": "SH", "name": "countries"}]
}');
END;
/
PL/SQL procedure successfully completed.
--
-- Enable AI profile in current session
--
SQL> EXEC DBMS_CLOUD_AI.SET_PROFILE('COHERE');
PL/SQL procedure successfully completed.
--
-- Get Profile in current session
--
SQL> SELECT DBMS_CLOUD_AI.get_profile() from dual;
DBMS_CLOUD_AI.GET_PROFILE()
--------------------------------------------------------------------------------
"COHERE"
--
-- Use AI
--
SQL> select ai how many customers exist;
CUSTOMER_COUNT
--------------
55500
SQL> EXEC DBMS_CLOUD_AI.DROP_PROFILE('COHERE');
PL/SQL procedure successfully completed.Das folgende Beispiel zeigt, wie Sie ein anderes Modell und benutzerdefinierte Attribute in Ihrem AI-Profil angeben:
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name => 'COHERE',
attributes =>
'{"provider": "cohere",
"credential_name": "COHERE_CRED",
"model": "cohere.command-a-03-2025",
"object_list": [{"owner": "ADB_USER"}],
"max_tokens":512,
"stop_tokens": [";"],
"temperature": 0.5,
"comments": true
}');
END;
/Übergeordnetes Thema: Beispiele für die Verwendung von Select AI
Beispiel: AI mit Azure OpenAI Service auswählen
Die folgenden Beispiele zeigen, wie Sie den Zugriff auf den Azure-Service OpenAI mit Ihrem API-Schlüssel aktivieren oder den Azure-Service-Principal OpenAI verwenden, ein KI-Profil erstellen und SQL aus Eingabeaufforderungen in natürlicher Sprache generieren können.
-- Create Credential for AI integration
--
EXEC
DBMS_CLOUD.CREATE_CREDENTIAL(
CREDENTIAL_NAME => 'AZURE_CRED',
username => 'AZUREAI',
password => 'your_api_token');
PL/SQL procedure successfully completed.
--
-- Grant Network ACL for OpenAI endpoint
--
BEGIN
DBMS_NETWORK_ACL_ADMIN.APPEND_HOST_ACE(
host => '<azure_resource_name>.openai.azure.com',
ace => xs$ace_type(privilege_list => xs$name_list('http'),
principal_name => 'ADB_USER',
principal_type => xs_acl.ptype_db)
);
END;
/
PL/SQL procedure successfully completed.
--
-- Create AI profile
--
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name=> 'AZUREAI',
attributes=> '{"provider": "azure",
"azure_resource_name": "<azure_resource_name>",
"azure_deployment_name": "<azure_deployment_name>"
"credential_name": "AZURE_CRED",
"object_list": [{"owner": "SH", "name": "customers"},
{"owner": "SH", "name": "countries"},
{"owner": "SH", "name": "supplementary_demographics"},
{"owner": "SH", "name": "profits"},
{"owner": "SH", "name": "promotions"},
{"owner": "SH", "name": "products"}],
"conversation": "true"
}');
END;
/
PL/SQL procedure successfully completed.
--
-- Enable AI profile in current session
--
EXEC DBMS_CLOUD_AI.SET_PROFILE('AZUREAI');
PL/SQL procedure successfully completed.
--
-- Get Profile in current session
--
SELECT DBMS_CLOUD_AI.get_profile() from dual;
DBMS_CLOUD_AI.GET_PROFILE()
--------------------------------------------------------------------------------
"AZUREAI"
--
-- Use AI
--
select ai how many customers exist;
CUSTOMER_COUNT
--------------
55500
select ai how many customers in San Francisco are married;
MARRIED_CUSTOMERS
-----------------
18
select ai showsql how many customers in San Francisco are married;
RESPONSE
--------------------------------------------------------------------------------
SELECT COUNT(*) AS married_customers_count
FROM SH.CUSTOMERS c
WHERE c.CUST_CITY = 'San Francisco'
AND c.CUST_MARITAL_STATUS = 'Married'
select ai explainsql how many customers in San Francisco are married;
RESPONSE
--------------------------------------------------------------------------------
SELECT COUNT(*) AS customer_count
FROM SH.CUSTOMERS AS c
WHERE c.CUST_STATE_PROVINCE = 'San Francisco' AND c.CUST_MARITAL_STATUS = 'Married';
Explanation:
- We use the 'SH' table alias for the 'CUSTOMERS' table for better readability.
- The query uses the 'COUNT(*)' function to count the number of rows that match the given conditions.
- The 'WHERE' clause is used to filter the results:
- 'c.CUST_STATE_PROVINCE = 'San Francisco'' filters customers who have 'San Francisco' as their state or province.
- 'c.CUST_MARITAL_STATUS = 'Married'' filters customers who have 'Married' as their marital status.
The result of this query will give you the count of customers in San Francisco who are married, using the column alias 'customer_count' for the result.
Remember to adjust the table and column names based on your actual schema if they differ from the example.
Feel free to ask if you have more questions related to SQL or database in general.
select ai narrate what are the top 3 customers in San Francisco;
RESPONSE
--------------------------------------------------------------------------------
The top 3 customers in San Francisco are:
1. Hector Colven - Total amount sold: $52,025.99
2. Milburn Klemm - Total amount sold: $50,842.28
3. Gavin Xie - Total amount sold: $48,677.18
select ai chat what is Autonomous Database;
RESPONSE
--------------------------------------------------------------------------------
Autonomous Database is a cloud-based database service provided by Oracle. It is designed to automate many of the routine tasks involved in managing a database,
such as patching, tuning, and backups. Autonomous Database uses machine learning and automation to optimize performance, security, and availability, allowing
users to focus on their applications and data rather than database administration tasks. It offers both Autonomous Transaction Processing (ATP) for transactional
workloads and Autonomous Data Warehouse (ADW) for analytical workloads. Autonomous Database provides high performance, scalability, and reliability, making it
an ideal choice for modern cloud-based applications.
EXEC DBMS_CLOUD_AI.DROP_PROFILE('AZUREAI');
PL/SQL procedure successfully completed.Das folgende Beispiel zeigt, wie Sie ein anderes Modell in Ihrem AI-Profil angeben:
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name=>'AZUREAI',
attributes=>'{"provider": "azure",
"credential_name": "AZURE$PA",
"model": "gpt-3.5-turbo",
"object_list": [{"owner": "SH", "name": "customers"},
{"owner": "SH", "name": "countries"},
{"owner": "SH", "name": "supplementary_demographics"},
{"owner": "SH", "name": "profits"},
{"owner": "SH", "name": "promotions"},
{"owner": "SH", "name": "products"}],
"azure_resource_name": "<azure_resource_name>",
"azure_deployment_name": "<azure_deployment_name>"
}');
END;
/Beispiel: AI mit Azure OpenAI Service Principal auswählen
Stellen Sie als Datenbankadministrator eine Verbindung her, um Zugriff auf die Azure-Service-Principal-Authentifizierung zu erteilen, und erteilen Sie dem Benutzer (ADB_USER), der Select AI verwenden möchte, die Netzwerk-ACL-Berechtigungen. Informationen zum Zugriff auf Azure-Ressourcen finden Sie unter Azure-Service-Principal für den Zugriff auf Azure-Ressourcen verwenden.
Hinweis
Nur ein DBA-Benutzer kann
Nur ein DBA-Benutzer kann
EXECUTE-Berechtigungen und die Netzwerk-ACL-Prozedur ausführen.
-- Connect as ADMIN user and enable Azure service principal authentication.
BEGIN
DBMS_CLOUD_ADMIN.ENABLE_PRINCIPAL_AUTH(provider => 'AZURE',
params => JSON_OBJECT('azure_tenantid' value 'azure_tenantid'));
END;
/
-- Copy the consent url from cloud_integrations view and consents the ADB-S application.
SQL> select param_value from CLOUD_INTEGRATIONS where param_name = 'azure_consent_url';
PARAM_VALUE
--------------------------------------------------------------------------------
https://login.microsoftonline.com/<tenant_id>/oauth2/v2.0/authorize?client_id=<client_id>&response_type=code&scope=User.read
-- On the Azure OpenAI IAM console, search for the Azure application name and assign the permission to the application.
-- You can get the application name in the cloud_integrations view.
SQL> select param_value from CLOUD_INTEGRATIONS where param_name = 'azure_app_name';
PARAM_VALUE
--------------------------------------------------------------------------------
ADBS_APP_DATABASE_OCID
--
-- Grant Network ACL for Azure OpenAI endpoint
--SQL> BEGIN
DBMS_NETWORK_ACL_ADMIN.APPEND_HOST_ACE(
host => 'azure_resource_name.openai.azure.com',
ace => xs$ace_type(privilege_list => xs$name_list('http'),
principal_name => 'ADB_USER',
principal_type => xs_acl.ptype_db)
);
END;
/
PL/SQL procedure successfully completed.
--
-- Create AI profile
--
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name=>'AZUREAI',
attributes=>'{"provider": "azure",
"credential_name": "AZURE$PA",
"object_list": [{"owner": "SH", "name": "customers"},
{"owner": "SH", "name": "countries"},
{"owner": "SH", "name": "supplementary_demographics"},
{"owner": "SH", "name": "profits"},
{"owner": "SH", "name": "promotions"},
{"owner": "SH", "name": "products"}],
"azure_resource_name": "<azure_resource_name>",
"azure_deployment_name": "<azure_deployment_name>"
}');
END;
/
PL/SQL procedure successfully completed.
--
-- Enable AI profile in current session
--
EXEC DBMS_CLOUD_AI.SET_PROFILE('AZUREAI');
PL/SQL procedure successfully completed.
--
-- Get Profile in current session
--
SELECT DBMS_CLOUD_AI.get_profile() from dual;
DBMS_CLOUD_AI.GET_PROFILE()
--------------------------------------------------------------------------------
"AZUREAI"
--
-- Use AI
--
select ai how many customers exist;
CUSTOMER_COUNT
--------------
55500
select ai how many customers in San Francisco are married;
MARRIED_CUSTOMERS
-----------------
18
select ai showsql how many customers in San Francisco are married;
RESPONSE
--------------------------------------------------------------------------------
SELECT COUNT(*) AS married_customers_count
FROM SH.CUSTOMERS c
WHERE c.CUST_CITY = 'San Francisco'
AND c.CUST_MARITAL_STATUS = 'Married'
select ai explainsql how many customers in San Francisco are married;
RESPONSE
--------------------------------------------------------------------------------
SELECT COUNT(*) AS customer_count
FROM SH.CUSTOMERS AS c
WHERE c.CUST_STATE_PROVINCE = 'San Francisco' AND c.CUST_MARITAL_STATUS = 'Married';
Explanation:
- We use the 'SH' table alias for the 'CUSTOMERS' table for better readability.
- The query uses the 'COUNT(*)' function to count the number of rows that match the given conditions.
- The 'WHERE' clause is used to filter the results:
- 'c.CUST_STATE_PROVINCE = 'San Francisco'' filters customers who have 'San Francisco' as their state or province.
- 'c.CUST_MARITAL_STATUS = 'Married'' filters customers who have 'Married' as their marital status.
The result of this query will give you the count of customers in San Francisco who are married, using the column alias 'customer_count' for the result.
Remember to adjust the table and column names based on your actual schema if they differ from the example.
Feel free to ask if you have more questions related to SQL or database in general.
select ai narrate what are the top 3 customers in San Francisco;
RESPONSE
--------------------------------------------------------------------------------
The top 3 customers in San Francisco are:
1. Hector Colven - Total amount sold: $52,025.99
2. Milburn Klemm - Total amount sold: $50,842.28
3. Gavin Xie - Total amount sold: $48,677.18
select ai chat what is Autonomous Database;
RESPONSE
--------------------------------------------------------------------------------
Autonomous Database is a cloud-based database service provided by Oracle. It is designed to automate many of the routine tasks involved in managing a database,
such as patching, tuning, and backups. Autonomous Database uses machine learning and automation to optimize performance, security, and availability, allowing us
ers to focus on their applications and data rather than database administration tasks. It offers both Autonomous Transaction Processing (ATP) for transactional
workloads and Autonomous Data Warehouse (ADW) for analytical workloads. Autonomous Database provides high performance, scalability, and reliability, making it
an ideal choice for modern cloud-based applications.
EXEC DBMS_CLOUD_AI.DROP_PROFILE('AZUREAI');
PL/SQL procedure successfully completed.Übergeordnetes Thema: Beispiele für die Verwendung von Select AI
Beispiel: AI mit Google auswählen
Dieses Beispiel zeigt, wie Sie mit Google SQL aus Eingabeaufforderungen in natürlicher Sprache generieren, ausführen und erklären oder mit dem Google Gemini LLM chatten können.
Das folgende Beispiel zeigt die Verwendung von Google als KI-Anbieter. Das Beispiel zeigt, wie Sie mit Ihrem Google-API-Signaturschlüssel den Netzwerkzugriff ermöglichen, ein KI-Profil erstellen und mithilfe von AI-Aktionen zum Auswählen SQL-Abfragen aus Eingabeaufforderungen in natürlicher Sprache und Chatantworten generieren.
--Grants EXECUTE privilege to ADB_USER
--
SQL> grant EXECUTE on DBMS_CLOUD_AI to ADB_USER;
--
-- Create Credential for AI provider
--
SQL> BEGIN
DBMS_CLOUD.CREATE_CREDENTIAL(
credential_name => 'GOOGLE_CRED',
username => 'GOOGLE',
password => '<your_api_key>'
);
END;
/
PL/SQL procedure successfully completed.
--
-- Grant Network ACL for Google endpoint
--
SQL>
SQL> BEGIN
DBMS_NETWORK_ACL_ADB_USER.APPEND_HOST_ACE(
host => 'generativelanguage.googleapis.com',
ace => xs$ace_type(privilege_list => xs$name_list('http'),
principal_name => 'ADB_USER',
principal_type => xs_acl.ptype_db)
);
END;
/
PL/SQL procedure successfully completed.
--
-- Create AI profile
--
SQL> BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name =>'GOOGLE',
attributes =>'{"provider": "google",
"credential_name": "GOOGLE_CRED",
"object_list": [{"owner": "SH", "name": "customers"},
{"owner": "SH", "name": "countries"},
{"owner": "SH", "name": "supplementary_demographics"},
{"owner": "SH", "name": "profits"},
{"owner": "SH", "name": "promotions"},
{"owner": "SH", "name": "products"}]
}');
END;
/
PL/SQL procedure successfully completed.
--
-- Enable AI profile in current session
--
SQL> EXEC DBMS_CLOUD_AI.SET_PROFILE('GOOGLE');
PL/SQL procedure successfully completed.
--
-- Use AI
--
SQL> select ai how many customers exist;
CUSTOMER_COUNT
--------------
55500
SQL> select ai how many customers in San Francisco are married;
MARRIED_CUSTOMERS
-----------------
18
SQL> select ai showsql how many customers in San Francisco are married;
RESPONSE
--------------------------------------------------------------------------------
SELECT COUNT(*) AS married_customers_count
FROM SH.CUSTOMERS c
WHERE c.CUST_CITY = 'San Francisco'
AND c.CUST_MARITAL_STATUS = 'Married'
SQL> select ai explainsql how many customers in San Francisco are married;
RESPONSE
--------------------------------------------------------------------------------
SELECT COUNT(*) AS customer_count
FROM SH.CUSTOMERS AS c
WHERE c.CUST_STATE_PROVINCE = 'San Francisco' AND c.CUST_MARITAL_STATUS = 'Married';
Explanation:
- We use the 'SH' table alias for the 'CUSTOMERS' table for better readability.
- The query uses the 'COUNT(*)' function to count the number of rows that match the given conditions.
- The 'WHERE' clause is used to filter the results:
- 'c.CUST_STATE_PROVINCE = 'San Francisco'' filters customers who have 'San Francisco' as their state or province.
- 'c.CUST_MARITAL_STATUS = 'Married'' filters customers who have 'Married' as their marital status.
The result of this query will give you the count of customers in San Francisco who are married, using the column alias 'customer_count' for the result.
Remember to adjust the table and column names based on your actual schema if they differ from the example.
Feel free to ask if you have more questions related to SQL or database in general.
SQL> select ai narrate what are the top 3 customers in San Francisco;
RESPONSE
--------------------------------------------------------------------------------
The top 3 customers in San Francisco are:
1. Hector Colven - Total amount sold: $52,025.99
2. Milburn Klemm - Total amount sold: $50,842.28
3. Gavin Xie - Total amount sold: $48,677.18
SQL> select ai chat what is Autonomous Database;
RESPONSE
--------------------------------------------------------------------------------
Autonomous Database is a cloud-based database service provided by Oracle. It is designed to automate many of the routine tasks involved in managing a database,
such as patching, tuning, and backups. Autonomous Database uses machine learning and automation to optimize performance, security, and availability, allowing
users to focus on their applications and data rather than database administration tasks. It offers both Autonomous Transaction Processing (ATP) for transactional
workloads and Autonomous Data Warehouse (ADW) for analytical workloads. Autonomous Database provides high performance, scalability, and reliability, making it
an ideal choice for modern cloud-based applications.
--
--Drop the profile
--
EXEC DBMS_CLOUD_AI.DROP_PROFILE('GOOGLE');
PL/SQL procedure successfully completed. Das folgende Beispiel zeigt, wie Sie ein anderes Modell in Ihrem AI-Profil angeben:
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name =>'GOOGLE',
attributes =>'{"provider": "google",
"credential_name": "GOOGLE_CRED",
"model": "gemini-1.5-pro",
"object_list": [{"owner": "SH", "name": "customers"},
{"owner": "SH", "name": "countries"},
{"owner": "SH", "name": "supplementary_demographics"},
{"owner": "SH", "name": "profits"},
{"owner": "SH", "name": "promotions"},
{"owner": "SH", "name": "products"}]
}');
END;
/Übergeordnetes Thema: Beispiele für die Verwendung von Select AI
Beispiel: AI mit Anthropic auswählen
Dieses Beispiel zeigt, wie Sie mit Anthropic SQL aus Eingabeaufforderungen in natürlicher Sprache generieren, ausführen und erklären oder mit Anthropic Claude LLM chatten können.
Das folgende Beispiel zeigt die Verwendung von Anthropic als AI-Provider. Das Beispiel zeigt, wie Sie mit Ihrem Anthropic API-Signaturschlüssel Netzwerkzugriff bereitstellen, ein KI-Profil erstellen und mit Select AI-Aktionen SQL-Abfragen aus Eingabeaufforderungen in natürlicher Sprache generieren und mit dem Anthropic Claude LLM chatten.
Informationen zu den Profilattributen finden Sie unter Profilattribute.
--Grant EXECUTE privilege to ADB_USER
SQL>GRANT EXECUTE on DBMS_CLOUD_AI to ADB_USER;
--
-- Create Credential for AI provider
--
SQL>BEGIN
DBMS_CLOUD.CREATE_CREDENTIAL(
credential_name => 'ANTHROPIC_CRED',
username => 'ANTHROPIC',
password => '<your api key>'
);
END;
/
PL/SQL procedure successfully completed.
--
-- Grant Network ACL for Anthropic endpoint
--
SQL>BEGIN
DBMS_NETWORK_ACL_ADB_USER.APPEND_HOST_ACE(
host => 'api.anthropic.com',
ace => xs$ace_type(privilege_list => xs$name_list('http'),
principal_name => 'ADB_USER',
principal_type => xs_acl.ptype_db)
);
END;
/
PL/SQL procedure successfully completed.
--
-- Create AI profile
--
SQL>BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name =>'ANTHROPIC',
attributes =>'{"provider": "anthropic",
"credential_name": "ANTHROPIC_CRED",
"object_list": [{"owner": "SH", "name": "customers"},
{"owner": "SH", "name": "countries"},
{"owner": "SH", "name": "supplementary_demographics"},
{"owner": "SH", "name": "profits"},
{"owner": "SH", "name": "promotions"},
{"owner": "SH", "name": "products"}]
}');
END;
/
PL/SQL procedure successfully completed.
--
-- Enable AI profile in current session
--
SQL>EXEC DBMS_CLOUD_AI.SET_PROFILE('ANTHROPIC');
PL/SQL procedure successfully completed.
--
-- Use AI
--
SQL> select ai how many customers exist;
CUSTOMER_COUNT
--------------
55500
SQL> select ai how many customers in San Francisco are married;
MARRIED_CUSTOMERS
-----------------
18
SQL> select ai showsql how many customers in San Francisco are married;
RESPONSE
--------------------------------------------------------------------------------
SELECT COUNT(*) AS married_customers_count
FROM SH.CUSTOMERS c
WHERE c.CUST_CITY = 'San Francisco'
AND c.CUST_MARITAL_STATUS = 'Married'
SQL> select ai explainsql how many customers in San Francisco are married;
RESPONSE
--------------------------------------------------------------------------------
SELECT COUNT(*) AS customer_count
FROM SH.CUSTOMERS AS c
WHERE c.CUST_STATE_PROVINCE = 'San Francisco' AND c.CUST_MARITAL_STATUS = 'Married';
Explanation:
- We use the 'SH' table alias for the 'CUSTOMERS' table for better readability.
- The query uses the 'COUNT(*)' function to count the number of rows that match the given conditions.
- The 'WHERE' clause is used to filter the results:
- 'c.CUST_STATE_PROVINCE = 'San Francisco'' filters customers who have 'San Francisco' as their state or province.
- 'c.CUST_MARITAL_STATUS = 'Married'' filters customers who have 'Married' as their marital status.
The result of this query will give you the count of customers in San Francisco who are married, using the column alias 'customer_count' for the result.
Remember to adjust the table and column names based on your actual schema if they differ from the example.
Feel free to ask if you have more questions related to SQL or database in general.
SQL> select ai narrate what are the top 3 customers in San Francisco;
RESPONSE
--------------------------------------------------------------------------------
The top 3 customers in San Francisco are:
1. Hector Colven - Total amount sold: $52,025.99
2. Milburn Klemm - Total amount sold: $50,842.28
3. Gavin Xie - Total amount sold: $48,677.18
SQL> select ai chat what is Autonomous Database;
RESPONSE
--------------------------------------------------------------------------------
Autonomous Database is a cloud-based database service provided by Oracle. It is designed to automate many of the routine tasks involved in managing a database,
such as patching, tuning, and backups. Autonomous Database uses machine learning and automation to optimize performance, security, and availability, allowing
users to focus on their applications and data rather than database administration tasks. It offers both Autonomous Transaction Processing (ATP) for transactional
workloads and Autonomous Data Warehouse (ADW) for analytical workloads. Autonomous Database provides high performance, scalability, and reliability, making it
an ideal choice for modern cloud-based applications.
--
--Drop the profile
--
EXEC DBMS_CLOUD_AI.DROP_PROFILE('ANTHROPIC');
PL/SQL procedure successfully completed.
Das folgende Beispiel zeigt, wie Sie ein anderes Modell in Ihrem AI-Profil angeben:
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name =>'ANTHROPIC',
attributes =>'{"provider": "anthropic",
"credential_name": "ANTHROPIC_CRED",
"model": "claude-3-opus-20240229",
"object_list": [{"owner": "SH", "name": "customers"},
{"owner": "SH", "name": "countries"},
{"owner": "SH", "name": "supplementary_demographics"},
{"owner": "SH", "name": "profits"},
{"owner": "SH", "name": "promotions"},
{"owner": "SH", "name": "products"}]
}');
END;
/Übergeordnetes Thema: Beispiele für die Verwendung von Select AI
Beispiel: AI mit umarmendem Gesicht auswählen
Dieses Beispiel zeigt, wie Sie mit Hugging Face SQL aus Eingabeaufforderungen in natürlicher Sprache oder Chat mit dem Hugging Face LLM generieren, ausführen und erklären können.
Das folgende Beispiel zeigt die Verwendung von Hugging Face als KI-Provider. Das Beispiel zeigt, wie Sie mit Ihrem Signaturschlüssel für die Hugging Face-API Netzwerkzugriff bereitstellen, ein KI-Profil erstellen und mit Select AI-Aktionen SQL-Abfragen aus Eingabeaufforderungen in natürlicher Sprache generieren und mit dem Hugging Face LLM chatten.
--Grant EXECUTE privilege to ADB_USER
SQL>GRANT EXECUTE on DBMS_CLOUD_AI to ADB_USER;
--
-- Create Credential for AI provider
--
SQL>BEGIN
DBMS_CLOUD.CREATE_CREDENTIAL(
credential_name => 'HF_CRED',
username => 'HF',
password => '<your_api_key>'
);
END;
/
PL/SQL procedure successfully completed.
--
-- Grant Network ACL for Hugging Face endpoint
--
SQL>BEGIN
DBMS_NETWORK_ACL_ADMIN.APPEND_HOST_ACE(
host => 'api-inference.huggingface.co',
ace => xs$ace_type(privilege_list => xs$name_list('http'),
principal_name => 'ADB_USER',
principal_type => xs_acl.ptype_db)
);
END;
/
PL/SQL procedure successfully completed.
--
-- Create AI profile
--
SQL>BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name =>'HF',
attributes =>'{"provider": "huggingface",
"credential_name": "HF_CRED",
"object_list": [{"owner": "SH", "name": "customers"},
{"owner": "SH", "name": "countries"},
{"owner": "SH", "name": "supplementary_demographics"},
{"owner": "SH", "name": "profits"},
{"owner": "SH", "name": "promotions"},
{"owner": "SH", "name": "products"}],
"model" : "Qwen/Qwen2.5-72B-Instruct"
}');
END;
/
PL/SQL procedure successfully completed.
--
-- Enable AI profile in current session
--
SQL>EXEC DBMS_CLOUD_AI.SET_PROFILE('HF');
PL/SQL procedure successfully completed.
--
-- Use AI
--SQL> select ai how many customers exist;
Customer_Count
--------------
55500
SQL> select ai how many customers in San Francisco are married;
Married_Customers
-----------------
46
SQL> select ai showsql how many customers in San Francisco are married;
RESPONSE
------------------------------------------------------------
SELECT COUNT("CUST_ID") AS "Married_Customers"
FROM "SH"."CUSTOMERS" "C"
WHERE "CUST_CITY" = 'San Francisco' AND "CUST_MARITAL_STATUS
" = 'Married'
SQL> select ai explainsql how many customers in San Francisco are married;
RESPONSE
------------------------------------------------------------
To answer the question "How many customers in San Francisco are married?", we need to query the "SH"."CUSTOMERS" table and filter the results based on the city and marital status.
We will use table aliases to make the query more readable and ensure that the string comparisons follow the specified rules.
Here is the Oracle SQL query:
```sql
SELECT COUNT("CUST_ID") AS "Married_Customers_in_San_Francisco"
FROM "SH"."CUSTOMERS" c
WHERE c."CUST_CITY" = 'San Francisco' -- Case insensitive comparison
AND UPPER(c."CUST_MARITAL_STATUS") = UPPER('Married'); --
Case insensitive comparison
```
### Explanation:
1. **Table Alias**:
RESPONSE
------------------------------------------------------------
- We use the alias `c` for the "SH"."CUSTOMERS" table to make the query more readable.
2. **Column Selection**:
- We select the count of "CUST_ID" to get the number of customers who meet the criteria. We alias this count as "Married_Customers_in_San_Francisco" for clarity.
3. **WHERE Clause**:
- **City Filter**: `c."CUST_CITY" = 'San Francisco'`
- Since 'San Francisco' is not in double quotes, we use a case-insensitive comparison.
- **Marital Status Filter**: `UPPER(c."CUST_MARITAL_STATUS") = UPPER('Married')`
- Since 'Married' is not in double quotes, we use a case-insensitive comparison by applying the `UPPER` function to both sides of the comparison.
This query will return the number of customers in San Francisco who are married.
SQL> select ai narrate what are the top 3 customers in San Francisco;
RESPONSE
------------------------------------------------------------
The top 3 customers in San Francisco are:
- Hector Colven, with a customer ID of 8866.
- Milburn Klemm, with a customer ID of 1944.
- Gavin Xie, with a customer ID of 2579.
These customers have the highest total sales among all customers in San Francisco.
SQL> select ai chat what is Autonomous Database;
RESPONSE
------------------------------------------------------------
An Autonomous Database is a type of database management system that uses artificial intelligence (AI) and machine learning (ML) to automate many of the routine tasks typically performed by database administrators (DBAs). These tasks include provisioning, patching, backups, tuning, and security. The goal of an autonomous database is to reduce the need for human intervention, minimize errors, and optimize performance,thereby allowing organizations to focus on more strategic activities.
### Key Features of Autonomous Databases:
RESPONSE
------------------------------------------------------------
1. **Automated Provisioning**: The database can be set up and configured automatically, reducing the time and effort required to get it up and running.
2. **Self-Patching and Updates**: The database automatically applies security patches and updates without downtime, ensuring that the system remains secure and up-to-date.
3. **Self-Tuning**: The database continuously monitors its performance and adjusts settings to optimize query execution and resource utilization.
4. **Self-Backup and Recovery**: Automated backup and recovery processes ensure that data is protected and can be restored quickly in the event of a failure.
5. **Security**: Advanced security features, including threat detection and response, are built into the database to protect against cyber threats.
6. **Scalability**: The database can automatically scale resources up or down based on demand, ensuring optimal performance and cost efficiency.
7. **Monitoring and Diagnostics**: Real-time monitoring and diagnostics help identify and resolve issues before they impact performance.
RESPONSE
------------------------------------------------------------
### Benefits of Autonomous Databases:
- **Reduced Operational Costs**: By automating routine tasks, the need for dedicated DBAs is reduced, lowering operational costs.
- **Improved Reliability**: Automated processes reduce the risk of human error, leading to more reliable and consistent performance.
- **Enhanced Security**: Continuous monitoring and automated security measures help protect against threats.
- **Faster Time to Market**: Automated provisioning and tuning allow applications to be deployed more quickly.
RESPONSE
------------------------------------------------------------
- **Scalability and Flexibility**: The ability to scale resources automatically ensures that the database can handle varying workloads efficiently.
### Use Cases:
- **Cloud Applications**: Autonomous databases are particularly useful in cloud environments where scalability and reliability are critical.
- **Data Warehousing**: They can handle large volumes of data and complex queries, making them ideal for data warehousing and analytics.
RESPONSE
------------------------------------------------------------
- **IoT and Real-Time Data Processing**: They can process and analyze real-time data from IoT devices efficiently.
- **E-commerce**: They can handle high transaction volumes and ensure fast response times for online shopping platforms.
### Examples of Autonomous Databases:
- **Oracle Autonomous Database**: One of the first and most well-known autonomous databases, offering both transactional
and data warehousing capabilities.
- **Amazon Aurora**: A managed relational database service that includes automated scaling, patching, and backups.
- **Microsoft Azure SQL Database Managed Instance**: Provides a high level of automation and management for SQL Server databases in the cloud.
- **Google Cloud Spanner**: A globally distributed, horizontally scalable relational database that is highly available and consistent.
Autonomous databases represent a significant advancement in database technology, offering organizations a more efficient, secure, and cost-effective way to manage their data.
SQL> EXEC DBMS_CLOUD_AI.DROP_PROFILE('HF');
PL/SQL procedure successfully completed.Übergeordnetes Thema: Beispiele für die Verwendung von Select AI
Beispiel: Unterhaltungen in Select AI aktivieren
Dieses Beispiel veranschaulicht die Aktivierung von Unterhaltungen in Select AI.
Hinweis
Nur ein DBA kann
Nur ein DBA kann
EXECUTE-Berechtigungen und die Netzwerk-ACL-Prozedur ausführen.
Erstellen Sie Ihr KI-Profil. Setzen Sie das Attribut conversation im Profil auf true. Diese Aktion umfasst Inhalte aus früheren Interaktionen oder Prompts, möglicherweise einschließlich Schemametadaten, und legen Sie Ihr Profil fest. Sobald das Profil aktiviert ist, können Sie mit Unterhaltungen mit Ihren Daten beginnen. Verwenden Sie die natürliche Sprache, um Fragen zu stellen und bei Bedarf nachzugehen.
--Grants EXECUTE privilege to ADB_USER
--
SQL> grant execute on DBMS_CLOUD_AI to ADB_USER;
-- Grant Network ACL for OpenAI endpoint
--
SQL> BEGIN
DBMS_NETWORK_ACL_ADMIN.APPEND_HOST_ACE(
host => 'api.openai.com',
ace => xs$ace_type(privilege_list => xs$name_list('http'),
principal_name => 'ADB_USER',
principal_type => xs_acl.ptype_db)
);
END;
/
PL/SQL procedure successfully completed.
--
-- Create Credential for AI provider
--
EXEC
DBMS_CLOUD.CREATE_CREDENTIAL(
CREDENTIAL_NAME => 'OPENAI_CRED',
username => 'OPENAI',
password => '<your_api_token>');
PL/SQL procedure successfully completed.
--
-- Create AI profile
--
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name => 'OPENAI',
attributes =>'{"provider": "openai",
"credential_name": "OPENAI_CRED",
"object_list": [{"owner": "SH", "name": "customers"},
{"owner": "SH", "name": "countries"},
{"owner": "SH", "name": "supplementary_demographics"},
{"owner": "SH", "name": "profits"},
{"owner": "SH", "name": "promotions"},
{"owner": "SH", "name": "products"}],
"conversation": "true"
}');
END;
/
PL/SQL procedure successfully completed.
--
-- Enable AI profile in current session
--
SQL> EXEC DBMS_CLOUD_AI.SET_PROFILE('OPENAI');
PL/SQL procedure successfully completed.
--
-- Get Profile in current session
--
SQL> SELECT DBMS_CLOUD_AI.get_profile() from dual;
DBMS_CLOUD_AI.GET_PROFILE()
--------------------------------------------------------------------------------
"OPENAI"
--
-- Use AI
--
what are the total number of customers;
CUSTOMER_COUNT
--------------
55500
break out count of customers by country;
RESPONSE
-----------------
COUNTRY_NAME CUSTOMER_COUNT
Italy 7780
Brazil 832
Japan 624
United Kingdom 7557
Germany 8173
United States of America 18520
France 3833
Canada 2010
Spain 2039
China 712
Singapore 597
New Zealand 244
Poland 708
Australia 831
Argentina 403
Denmark 383
South Africa 88
Saudi Arabia 75
Turkey 91
what age group is most common;
RESPONSE
--------------------------------------------------------------------------------
AGE_GROUP CUSTOMER_COUNT
65+ 28226
select ai keep the top 5 customers and their country by their purchases and include a rank in the result;
RESPONSE
--------------------------------------------------------------------------------
RANK CUSTOMER_NAME COUNTRY PURCHASES
1 Abigail Ruddy Japan 276
2 Abigail Ruddy Italy 168
3 Abigail Ruddy Japan 74
3 Abner Robbinette Germany 74
5 Abner Everett France 68
SQL> EXEC DBMS_CLOUD_AI.DROP_PROFILE('OPENAI');
PL/SQL procedure successfully completed.Übergeordnetes Thema: Beispiele für die Verwendung von Select AI
Beispiel: Select AI mit RAG einrichten und verwenden
In diesem Beispiel werden Sie durch das Einrichten von Zugangsdaten, das Konfigurieren des Netzwerkzugriffs und das Erstellen eines Vektorindex für die Integration von Cloud-Services des OCI Generative AI Vektorspeichers mit OpenAI mit Oracle Autonomous Database geführt.
Das Setup endet mit der Erstellung eines KI-Profils, das den Vektorindex verwendet, um LLM-Antworten zu verbessern. Schließlich verwendet dieses Beispiel die Aktion "AI narrate auswählen", die eine Antwort zurückgibt, die mit Informationen aus der angegebenen Vektordatenbank erweitert wurde.
Das folgende Beispiel zeigt die Erstellung und Abfrage von Vektorindizes in Oracle 23ai.
--Grants EXECUTE privilege to ADB_USER
GRANT EXECUTE on DBMS_CLOUD_AI to ADB_USER;
--Grants EXECUTE privilege DBMS_CLOUD_PIPELINE to ADB_USER
GRANT EXECUTE on DBMS_CLOUD_PIPELINE to ADB_USER;
-- Create the OpenAI credential
BEGIN
DBMS_CLOUD.CREATE_CREDENTIAL(
credential_name => 'OPENAI_CRED',
username => 'OPENAI_CRED',
password => '<your_api_key>'
);
END;
/
PL/SQL procedure successfully completed.
-- Append the OpenAI endpoint
BEGIN
DBMS_NETWORK_ACL_ADMIN.APPEND_HOST_ACE(
host => 'api.openai.com',
ace => xs$ace_type(privilege_list => xs$name_list('http'),
principal_name => 'ADB_USER',
principal_type => xs_acl.ptype_db)
);
END;
/
PL/SQL procedure successfully completed.
-- Create the object store credential
BEGIN
DBMS_CLOUD.CREATE_CREDENTIAL(
credential_name => 'OCI_CRED',
username => '<your_username>',
password => '<OCI_profile_password>'
);
END;
/
PL/SQL procedure successfully completed.
-- Create the profile with the vector index.
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name =>'OPENAI_ORACLE',
attributes =>'{"provider": "openai",
"credential_name": "OPENAI_CRED",
"vector_index_name": "MY_INDEX",
"temperature": 0.2,
"max_tokens": 4096,
"model": "gpt-3.5-turbo-1106"
}');
END;
/
PL/SQL procedure successfully completed.
-- Set profile
EXEC DBMS_CLOUD_AI.SET_PROFILE('OPENAI_ORACLE');
PL/SQL procedure successfully completed.
-- create a vector index with the vector store name, object store location and
-- object store credential
BEGIN
DBMS_CLOUD_AI.CREATE_VECTOR_INDEX(
index_name => 'MY_INDEX',
attributes => '{"vector_db_provider": "oracle",
"location": "https://swiftobjectstorage.us-phoenix-1.oraclecloud.com/v1/my_namespace/my_bucket/my_data_folder",
"object_storage_credential_name": "OCI_CRED",
"profile_name": "OPENAI_ORACLE",
"vector_dimension": 1536,
"vector_distance_metric": "cosine",
"chunk_overlap":128,
"chunk_size":1024
}');
END;
/
PL/SQL procedure successfully completed.
-- After the vector index is populated, we can now query the index.
-- Set profile
EXEC DBMS_CLOUD_AI.SET_PROFILE('OPENAI_ORACLE');
PL/SQL procedure successfully completed.
-- Select AI answers the question with the knowledge available in the vector database.
set pages 1000
set linesize 150
SELECT AI narrate how can I deploy an oracle machine learning model;
RESPONSE
To deploy an Oracle Machine Learning model, you would first build your model within the Oracle database. Once your in-database models are built, they become immediately available for use, for instance, through a SQL query using the prediction operators built into the SQL language.
The model scoring, like model building, occurs directly in the database, eliminating the need for a separate engine or environment within which the model and corresponding algorithm code operate. You can also use models from a different schema (user account) if the appropriate permissions are in place.
Sources:
- Manage-your-models-with-Oracle-Machine-Learning-on-Autonomous-Database.txt (https://objectstorage.../v1/my_namespace/my_bucket/my_data_folder/Manage-your-models-with-Oracle-Machine-Learning-on-Autonomous-Database.txt)
- Develop-and-deploy-machine-learning-models-using-Oracle-Autonomous-Database-Machine-Learning-and-APEX.txt (https://objectstorage.../v1/my_namespace/my_bucket/my_data_folder/Develop-and-deploy-machine-learning-models-using-Oracle-Autonomous-Database-Machine-Learning-and-APEX.txt)
Übergeordnetes Thema: Beispiele für die Verwendung von Select AI
Beispiel: AI mit datenbankinternen Transformer-Modellen auswählen
Dieses Beispiel zeigt, wie Sie ein vortrainiertes Transformer-Modell, das im Oracle-Objektspeicher gespeichert ist, in Ihre Oracle Database 23ai-Instanz importieren und dann das importierte datenbankinterne Modell im AI-Profil "Auswählen" verwenden können, um Vektoreinbettungen für Dokumentblöcke und Benutzer-Prompts zu generieren.
Um datenbankinterne Transformer-Modelle in Ihrem Select AI-Profil zu verwenden, müssen Sie Folgendes beachten:
-
Ihr vortrainiertes Modell, das in Ihre Oracle Database 23ai-Instanz importiert wurde.
-
optional Zugriff auf Oracle Object Storage.
Pretrained Transformer-Modell aus Oracle Object Storage in Oracle Database 23ai importieren
Lesen Sie die Schritte unter Vortrainierte Modelle im ONNX-Format für die Vektorgenerierung in der Datenbank importieren und das Blog Vortrainiertes Einbettungsgenerierungsmodell für Oracle Database 23ai, um ein vortrainiertes Transformer-Modell in Ihre Datenbank zu importieren.
Das folgende Beispiel zeigt, wie Sie ein vorgefertigtes Transformer-Modell aus dem Oracle-Objektspeicher in die Datenbank importieren und dann das importierte Modell anzeigen.
- Create a Directory object, or use an existing directory object
CREATE OR REPLACE DIRECTORY ONNX_DIR AS 'onnx_model';
-- Object storage bucket
VAR location_uri VARCHAR2(4000);
EXEC :location_uri := 'https://adwc4pm.objectstorage.us-ashburn-1.oci.customer-oci.com/p/eLddQappgBJ7jNi6Guz9m9LOtYe2u8LWY19GfgU8flFK4N9YgP4kTlrE9Px3pE12/n/adwc4pm/b/OML-Resources/o/';
-- Model file name
VAR file_name VARCHAR2(512);
EXEC :file_name := 'all_MiniLM_L12_v2.onnx';
-- Download ONNX model from object storage into the directory object
BEGIN
DBMS_CLOUD.GET_OBJECT(
credential_name => NULL,
directory_name => 'ONNX_DIR',
object_uri => :location_uri || :file_name);
END;
/
-- Load the ONNX model into the database
BEGIN
DBMS_VECTOR.LOAD_ONNX_MODEL(
directory => 'ONNX_DIR',
file_name => :file_name,
model_name => 'MY_ONNX_MODEL');
END;
/
-- Verify
SELECT model_name, algorithm, mining_function
FROM user_mining_models
WHERE model_name='MY_ONNX_MODEL';Datenbankinterne Transformer-Modelle in ausgewählten KI-Profilen verwenden
Diese Beispiele zeigen, wie datenbankinterne Transformer-Modelle in einem Select AI-Profil verwendet werden. Ein Profil ist nur für die Generierung von Vektoreinbettungen konfiguriert, während das andere sowohl AI-Aktionen auswählen als auch die Erstellung von Vektorindizes unterstützt.
Lesen Sie Beispiele für Berechtigungen zum Ausführen von Select AI, um die Voraussetzungen abzuschließen.
Im Folgenden finden Sie ein Beispiel für die Generierung von Vektoreinbettungen:
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name => 'EMBEDDING_PROFILE',
attributes => '{"provider" : "database",
"embedding_model": "MY_ONNX_MODEL"}'
);
END;
/Im Folgenden finden Sie ein Beispiel für allgemeine Select AI-Aktionen und Vektorindexgenerierung, bei denen Sie einen unterstützten AI-Provider angeben können. In diesem Beispiel werden das KI-Profil und die Zugangsdaten der OCI-Generation verwendet. Eine Liste der unterstützten Provider finden Sie unter KI-Provider und LLMs auswählen. Wenn Sie jedoch das datenbankinterne Transformatormodell zum Generieren von Vektoreinbettungen verwenden möchten, verwenden Sie "database: <MY_ONNX_MODEL>" im Attribut embedding_model:
BEGIN
DBMS_CLOUD.CREATE_CREDENTIAL(
credential_name => 'GENAI_CRED',
user_ocid => 'ocid1.user.oc1..aaaa...',
tenancy_ocid => 'ocid1.tenancy.oc1..aaaa...',
private_key => '<your_api_key>',
fingerprint => '<your_fingerprint>'
);
END;
/
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name => 'OCI_GENAI',
attributes => '{"provider": "oci",
"model": "meta.llama-3.3-70b-instruct",
"credential_name": "GENAI_CRED",
"vector_index_name": "MY_INDEX",
"embedding_model": "database: MY_ONNX_MODEL"}'
);
END;
/Select AI mit einem datenbankinternen Transformer-Modell aus einem anderen Schema verwenden
In diesem Beispiel wird gezeigt, wie Sie Select AI mit einem datenbankinternen Transformer-Modell verwenden, wenn ein anderer Schemaeigentümer Eigentümer des Modells ist. Geben Sie schema_name.object_name als vollqualifizierten Namen des Modells im Attribut embedding_model an. Wenn der aktuelle Benutzer der Schemaeigentümer ist oder Eigentümer des Modells ist, können Sie den Schemanamen weglassen.
Stellen Sie sicher, dass Sie über die folgenden Berechtigungen verfügen, wenn ein anderer Schemaeigentümer Eigentümer des Modells ist:
CREATE ANY MINING MODEL-SystemberechtigungSELECT ANY MINING MODEL-SystemberechtigungSELECT MINING MODEL-Objektberechtigung für das spezifische Modell
Um eine Systemberechtigung zu erteilen, müssen Sie entweder die Systemberechtigung mit ADMIN OPTION erhalten haben oder die Systemberechtigung GRANT ANY PRIVILEGE erhalten haben.
Informationen zu den Berechtigungen finden Sie unter Systemberechtigungen für Oracle Machine Learning for SQL.
Mit den folgenden Anweisungen kann ADB_USER1 Daten bewerten und Modelldetails in einem beliebigen Schema anzeigen, solange SELECT Zugriff auf die Daten erteilt wurde. ADB_USER1 kann jedoch nur Modelle im Schema ADB_USER1 erstellen.
GRANT CREATE MINING MODEL TO ADB_USER1;
GRANT SELECT ANY MINING MODEL TO ADB_USER1;
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name => 'OCI_GENAI',
attributes => '{"provider": "oci",
"credential_name": "GENAI_CRED",
"vector_index_name": "MY_INDEX",
"embedding_model": "database: ADB_USER1.MY_ONNX_MODEL"}'
);
END;
/Das folgende Beispiel zeigt, wie Sie den Objektnamen für das Modell angeben können, bei dem die Groß-/Kleinschreibung beachtet wird:
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name => 'OCI_GENAI',
attributes => '{"provider": "oci",
"credential_name": "GENAI_CRED",
"model": "meta.llama-3.3-70b-instruct",
"vector_index_name": "MY_INDEX",
"embedding_model": "database: \"adb_user1\".\"my_model\""}'
);
END;
/End-to-End-Beispiele mit verschiedenen KI-Providern
Diese Beispiele zeigen End-to-End-Schritte für die Verwendung des datenbankinternen Transformatormodells mit Select AI RAG. Ein Profil verwendet database als die provider, die ausschließlich zum Generieren von Einbettungsvektoren erstellt wurde, während das andere Profil oci als die provider verwendet, die für Select AI-Aktionen sowie für Vektorindizes erstellt wurden.
Prüfen Sie Voraussetzungen für ausgewählte KI ausführen, um die erforderlichen Berechtigungen bereitzustellen.
--Grant create any directory privilege to the user
GRANT CREATE ANY DIRECTORY to ADB_USER;
- Create a Directory object, or use an existing directory object
CREATE OR REPLACE DIRECTORY ONNX_DIR AS 'onnx_model';
-- Object storage bucket
VAR location_uri VARCHAR2(4000);
EXEC :location_uri := 'https://adwc4pm.objectstorage.us-ashburn-1.oci.customer-oci.com/p/eLddQappgBJ7jNi6Guz9m9LOtYe2u8LWY19GfgU8flFK4N9YgP4kTlrE9Px3pE12/n/adwc4pm/b/OML-Resources/o/';
-- Model file name
VAR file_name VARCHAR2(512);
EXEC :file_name := 'all_MiniLM_L12_v2.onnx';
-- Download ONNX model from object storage into the directory object
BEGIN
DBMS_CLOUD.GET_OBJECT(
credential_name => NULL,
directory_name => 'ONNX_DIR',
object_uri => :location_uri || :file_name);
END;
/
-- Load the ONNX model into the database
BEGIN
DBMS_VECTOR.LOAD_ONNX_MODEL(
directory => 'ONNX_DIR',
file_name => :file_name,
model_name => 'MY_ONNX_MODEL');
END;
/
-- Verify
SELECT model_name, algorithm, mining_function
FROM user_mining_models
WHERE model_name='MY_ONNX_MODEL';
--Administrator grants EXECUTE privilege to ADB_USER
GRANT EXECUTE on DBMS_CLOUD_AI to ADB_USER;
--Administrator grants EXECUTE privilege DBMS_CLOUD_PIPELINE to ADB_USER
GRANT EXECUTE on DBMS_CLOUD_PIPELINE to ADB_USER;
-- Create the object store credential
BEGIN
DBMS_CLOUD.CREATE_CREDENTIAL(
credential_name => 'OCI_CRED',
username => '<your_username>',
password => '<OCI_profile_password>'
);
END;
/
PL/SQL procedure successfully completed.
-- Create the profile with Oracle Database.
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name =>'EMBEDDING_PROFILE',
attributes =>'{"provider": "database",
"embedding_model": "MY_ONNX_MODEL"
}');
END;
/
PL/SQL procedure successfully completed.
-- Set profile
EXEC DBMS_CLOUD_AI.SET_PROFILE('EMBEDDING_PROFILE');
PL/SQL procedure successfully completed.
In diesem Beispiel wird oci als provider verwendet.
--Grant create any directory privilege to the user
GRANT CREATE ANY DIRECTORY to ADB_USER;
- Create a Directory object, or use an existing directory object
CREATE OR REPLACE DIRECTORY ONNX_DIR AS 'onnx_model';
-- Object storage bucket
VAR location_uri VARCHAR2(4000);
EXEC :location_uri := 'https://adwc4pm.objectstorage.us-ashburn-1.oci.customer-oci.com/p/eLddQappgBJ7jNi6Guz9m9LOtYe2u8LWY19GfgU8flFK4N9YgP4kTlrE9Px3pE12/n/adwc4pm/b/OML-Resources/o/';
-- Model file name
VAR file_name VARCHAR2(512);
EXEC :file_name := 'all_MiniLM_L12_v2.onnx';
-- Download ONNX model from object storage into the directory object
BEGIN
DBMS_CLOUD.GET_OBJECT(
credential_name => NULL,
directory_name => 'ONNX_DIR',
object_uri => :location_uri || :file_name);
END;
/
-- Load the ONNX model into the database
BEGIN
DBMS_VECTOR.LOAD_ONNX_MODEL(
directory => 'ONNX_DIR',
file_name => :file_name,
model_name => 'MY_ONNX_MODEL');
END;
/
-- Verify
SELECT model_name, algorithm, mining_function
FROM user_mining_models
WHERE model_name='MY_ONNX_MODEL';
–-Administrator Grants EXECUTE privilege to ADB_USER
GRANT EXECUTE on DBMS_CLOUD_AI to ADB_USER;
--Administrator Grants EXECUTE privilege DBMS_CLOUD_PIPELINE to ADB_USER
GRANT EXECUTE on DBMS_CLOUD_PIPELINE to ADB_USER;
-- Create the object store credential
BEGIN
DBMS_CLOUD.CREATE_CREDENTIAL(
credential_name => 'OCI_CRED',
username => '<your_username>',
password => '<OCI_profile_password>'
);
END;
/
--Create GenAI credentials
BEGIN
DBMS_CLOUD.CREATE_CREDENTIAL(
credential_name => 'GENAI_CRED',
user_ocid => 'ocid1.user.oc1..aaaa...',
tenancy_ocid => 'ocid1.tenancy.oc1..aaaa...',
private_key => '<your_api_key>',
fingerprint => '<your_fingerprint>'
);
END;
/
--Create OCI AI profile
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name => 'OCI_GENAI',
attributes => '{"provider": "oci",
"model": "meta.llama-3.3-70b-instruct",
"credential_name": "GENAI_CRED",
"vector_index_name": "MY_INDEX",
"embedding_model": "database: MY_ONNX_MODEL"}'
);
END;
/
-- Set profile
EXEC DBMS_CLOUD_AI.SET_PROFILE('OCI_GENAI');
PL/SQL procedure successfully completed.
-- create a vector index with the vector store name, object store location and
-- object store credential
BEGIN
DBMS_CLOUD_AI.CREATE_VECTOR_INDEX(
index_name => 'MY_INDEX',
attributes => '{"vector_db_provider": "oracle",
"location": "https://swiftobjectstorage.us-phoenix-1.oraclecloud.com/v1/my_namespace/my_bucket/my_data_folder",
"object_storage_credential_name": "OCI_CRED",
"profile_name": "OCI_GENAI",
"vector_dimension": 384,
"vector_distance_metric": "cosine",
"chunk_overlap":128,
"chunk_size":1024
}');
END;
/
PL/SQL procedure successfully completed.
-- Set profile
EXEC DBMS_CLOUD_AI.SET_PROFILE('OCI_GENAI');
PL/SQL procedure successfully completed.
-- Select AI answers the question with the knowledge available in the vector database.
set pages 1000
set linesize 150
SELECT AI narrate how can I deploy an oracle machine learning model;
RESPONSE
To deploy an Oracle Machine Learning model, you would first build your model within the Oracle database. Once your in-database models are
built, they become immediately available for use, for instance, through a SQL query using the prediction operators built into the SQL
language.
The model scoring, like model building, occurs directly in the database, eliminating the need for a separate engine or environment within
which the model and corresponding algorithm code operate. You can also use models from a different schema (user account) if the appropriate
permissions are in place.
Sources:
- Manage-your-models-with-Oracle-Machine-Learning-on-Autonomous-Database.txt (https://objectstorage.../v1/my_namespace/my_bucket/
my_data_folder/Manage-your-models-with-Oracle-Machine-Learning-on-Autonomous-Database.txt)
- Develop-and-deploy-machine-learning-models-using-Oracle-Autonomous-Database-Machine-Learning-and-APEX.txt
(https://objectstorage.../v1/my_namespace/my_bucket/my_data_folder/Develop-and-deploy-machine-learning-models-using-Oracle-Autonomous-
Database-Machine-Learning-and-APEX.txt)Übergeordnetes Thema: Beispiele für die Verwendung von Select AI
Beispiel: SQL-Abfragegenerierung verbessern
Diese Beispiele zeigen, wie Kommentare, Annotationen, Fremdschlüssel und referenzielle Integritäts-Constraints in Datenbanktabellen und -spalten die Generierung von SQL-Abfragen aus Eingabeaufforderungen in natürlicher Sprache verbessern können.
Beispiel: SQL-Generierung mit Tabellen- und Spaltenkommentaren verbessern
Wenn Tabellen- und Spaltenkommentare in den Datenbanktabellen vorhanden sind, aktivieren Sie den Parameter "comments":"true" in der Funktion DBMS_CLOUD_AI.CREATE_PROFILE, um Kommentare auf Tabellen- und Spaltenebene abzurufen. Die Kommentare werden den Metadaten des LLM hinzugefügt, um eine bessere SQL-Generierung zu ermöglichen.
-- Adding comments to table 1, table 2, and table 3. Table 1 has 3 columns, table 2 has 7 columns, table 3 has 2 columns.
-- TABLE1
COMMENT ON TABLE table1 IS 'Contains movies, movie titles and the year it was released';
COMMENT ON COLUMN table1.c1 IS 'movie ids. Use this column to join to other tables';
COMMENT ON COLUMN table1.c2 IS 'movie titles';
COMMENT ON COLUMN table1.c3 IS 'year the movie was released';
-- TABLE2
COMMENT ON TABLE table2 IS 'transactions for movie views - also known as streams';
COMMENT ON COLUMN table2.c1 IS 'day the movie was streamed';
COMMENT ON COLUMN table2.c2 IS 'genre ids. Use this column to join to other tables';
COMMENT ON COLUMN table2.c3 IS 'movie ids. Use this column to join to other tables';
COMMENT ON COLUMN table2.c4 IS 'customer ids. Use this column to join to other tables';
COMMENT ON COLUMN table2.c5 IS 'device used to stream, watch or view the movie';
COMMENT ON COLUMN table2.c6 IS 'sales from the movie';
COMMENT ON COLUMN table2.c7 IS 'number of views, watched, streamed';
-- TABLE3
COMMENT ON TABLE table3 IS 'Contains the genres';
COMMENT ON COLUMN table3.c1 IS 'genre id. use this column to join to other tables';
COMMENT ON COLUMN table3.c2 IS 'name of the genre';
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name => 'myprofile',
attributes =>
'{"provider": "azure",
"azure_resource_name": "my_resource",
"azure_deployment_name": "my_deployment",
"credential_name": "my_credential",
"comments":"true",
"object_list": [
{"owner": "moviestream", "name": "table1"},
{"owner": "moviestream", "name": "table2"},
{"owner": " moviestream", "name": "table3"}
]
}'
);
DBMS_CLOUD_AI.SET_PROFILE(
profile_name => 'myprofile'
);
END;
/
--Prompts
select ai what are our total views;
RESPONSE
-------------------------------------------------
TOTAL_VIEWS
-----------
97890562
select ai showsql what are our total views;
RESPONSE
-------------------------------------------------------------------------
SELECT SUM(QUANTITY_SOLD) AS total_views
FROM "moviestream"."table"
select ai what are our total views broken out by device;
DEVICE TOTAL_VIEWS
-------------------------- -----------
mac 14719238
iphone 20793516
ipad 15890590
pc 14715169
galaxy 10587343
pixel 10593551
lenovo 5294239
fire 5296916
8 rows selected.
select ai showsql what are our total views broken out by device;
RESPONSE
---------------------------------------------------------------------------------------
SELECT DEVICE, COUNT(*) AS TOTAL_VIEWS
FROM "moviestream"."table"
GROUP BY DEVICEBeispiel: SQL-Abfragegenerierung mit Tabellen- und Spaltenanmerkungen verbessern
Dieses Beispiel zeigt die Integration von Anmerkungen in Select AI, die in Oracle Database 23ai anwendbar sind. Die Annotationen werden den Metadaten hinzugefügt, die an das LLM gesendet werden.
Wenn in Ihrem Schema eine Tabelle mit Annotationen vorhanden ist, aktivieren Sie "annotations":"true" in der Funktion DBMS_CLOUD_AI.CREATE_PROFILE, um Select AI anzuweisen, den Metadaten Anmerkungen hinzuzufügen.
--
-- Annotations
--
CREATE TABLE emp2 (
empno NUMBER,
ename VARCHAR2(50) ANNOTATIONS (display 'lastname'),
salary NUMBER ANNOTATIONS ("person_salary", "column_hidden"),
deptno NUMBER ANNOTATIONS (display 'department')
)ANNOTATIONS (requires_audit 'yes', version '1.0', ówner 'HR Organization');
Table created.
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name => 'GOOGLE_ANNOTATIONS',
attributes => '{"provider": "google",
"credential_name": "GOOGLE_CRED",
"object_list": [{"owner": "ADB_USER", "name": "emp2"}],
"annotations" : "true"
}');
END;
/
PL/SQL procedure successfully completed.
EXEC DBMS_CLOUD_AI.SET_PROFILE('GOOGLE_ANNOTATIONS');
PL/SQL procedure successfully completed.Beispiel: SQL-Abfragegenerierung mit Fremdschlüssel- und referenziellen Schlüssel-Constraints verbessern
Dieses Beispiel zeigt die Fähigkeit des LLM, genaue JOIN-Bedingungen zu generieren, indem der Fremdschlüssel und die referentiellen Schlüssel-Constraints in die Metadaten des LLM abgerufen werden. Die Constraints für Fremdschlüssel und referenzielle Schlüssel stellen strukturierte Beziehungsdaten zwischen den Tabellen für das LLM bereit.
Aktivieren Sie "constraints":"true" in der Funktion DBMS_CLOUD_AI.CREATE_PROFILE, damit Select AI Fremdschlüssel und Referenzschlüssel abrufen kann.
--
-- Referential Constraints
--
CREATE TABLE dept_test (
deptno NUMBER PRIMARY KEY,
dname VARCHAR2(50)
);
Table created.
CREATE TABLE emp3 (
empno NUMBER PRIMARY KEY,
ename VARCHAR2(50),
salary NUMBER,
deptno NUMBER,
CONSTRAINT emp_dept_fk FOREIGN KEY (deptno) REFERENCES dept_test(deptno)
);
Table created.
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name=>'GOOGLE_CONSTRAINTS',
attribues =>'{"provider": "google",
"credential_name": "GOOGLE_CRED",
"object_list": [{"owner": "ADB_USER", "name": "dept_test"},
{"owner": "ADB_USER", "name": "emp3"}],
"constraints" : "true"
}');
END;
/
PL/SQL procedure successfully completed.
EXEC DBMS_CLOUD_AI.SET_PROFILE('GOOGLE_CONSTRAINTS');
PL/SQL procedure successfully completed.Beispiel: Relevante Tabellenmetadaten automatisch ermitteln
Diese Beispiele zeigen, wie Select AI relevante Tabellen automatisch erkennt und Metadaten nur für die spezifischen Tabellen sendet, die für die Abfrage in Oracle Database 23ai relevant sind. Um dieses Feature zu aktivieren, setzen Sie object_list_mode auf automated. Dadurch wird automatisch ein Vektorindex mit dem Namen <profile_name>_OBJECT_LIST_VECINDEX erstellt. Der Vektorindex wird mit Standardattributen und -werten wie refresh_rate, similarity_threshold und match_limit initialisiert. Sie können einige der Attribute über DBMS_CLOUD_AI.UPDATE_VECTOR_INDEX ändern. Weitere Informationen finden Sie unter Prozedur UPDATE_VECTOR_INDEX.
Ein Profil ist so konfiguriert, dass es object_list verwendet, um das Schema oder die Objekte im Schema anzugeben, während das andere nicht object_list angibt. Es wird jedoch dasselbe SQL-Konstrukt erwartet.
Lesen Sie Voraussetzungen für Select AI ausführen, um Zugriff auf das Package DBMS_CLOUD_AI zu erteilen und dem AI-Provider Netzwerkzugriff zu erteilen.
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name=>'OCI_AUTO',
attributes=>'{"provider": "oci",
"credential_name": "GENAI_CRED",
"object_list": [{"owner": "SH"}],
"oci_compartment_id": "ocid1.compartment.oc1..aaaa...",
"model" : "meta.llama-3.3-70b-instruct"
}');
END;
/
PL/SQL procedure successfully completed.
EXEC DBMS_CLOUD_AI.SET_PROFILE('OCI_AUTO');
PL/SQL procedure successfully completed.
select ai showsql how many customers in San Francisco are married;
RESPONSE
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
SELECT COUNT(DISTINCT c."CUST_ID") AS "NUMBER_OF_CUSTOMERS"
FROM "SH"."CUSTOMERS" c
WHERE UPPER(c."CUST_CITY") = UPPER('San Francisco')
AND UPPER(c."CUST_MARITAL_STATUS") = UPPER('married')Im folgenden Beispiel wird dasselbe Szenario ohne Verwendung von object_list verglichen. Wenn Sie object_list nicht angeben, wählt Select AI automatisch alle Objekte aus, die für das aktuelle Schema verfügbar sind.
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name=>'OCI_AUTO1',
attributes=>'{"provider": "oci",
"credential_name": "GENAI_CRED",
"oci_compartment_id": "ocid1.compartment.oc1..aaaa...",
"object_list_mode": "automated",
"model" : "meta.llama-3.3-70b-instruct"
}');
END;
/
PL/SQL procedure successfully completed.
EXEC DBMS_CLOUD_AI.SET_PROFILE('OCI_AUTO1');
PL/SQL procedure successfully completed.
select ai showsql how many customers in San Francisco are married?;
RESPONSE
----------------------------------------------------------------------------------------------------------------------------------------------------------------------
SELECT COUNT(c."CUST_ID") AS "Number_of_Customers"
FROM "SH"."CUSTOMERS" c
WHERE UPPER(c."CUST_CITY") = UPPER('San Francisco')
AND UPPER(c."CUST_MARITAL_STATUS") = UPPER('Married')Übergeordnetes Thema: Beispiele für die Verwendung von Select AI
Beispiel: Synthetische Daten generieren
In diesem Beispiel wird untersucht, wie Sie synthetische Daten generieren können, die den Eigenschaften und der Verteilung echter Daten entsprechen.
Das folgende Beispiel zeigt, wie Sie einige Tabellen in Ihrem Schema erstellen, OCI Generative AI als KI-Provider verwenden, um ein KI-Profil zu erstellen, Daten mit der Funktion DBMS_CLOUD_AI.GENERATE_SYNTHETIC_DATA in diese Tabellen zu synthetisieren und Antworten auf Eingabeaufforderungen in natürlicher Sprache mit Select AI abzufragen oder zu generieren.
--Create tables or use cloned tables
CREATE TABLE ADB_USER.Director (
director_id INT PRIMARY KEY,
name VARCHAR(100)
);
CREATE TABLE ADB_USER.Movie (
movie_id INT PRIMARY KEY,
title VARCHAR(100),
release_date DATE,
genre VARCHAR(50),
director_id INT,
FOREIGN KEY (director_id) REFERENCES ADB_USER.Director(director_id)
);
CREATE TABLE ADB_USER.Actor (
actor_id INT PRIMARY KEY,
name VARCHAR(100)
);
CREATE TABLE ADB_USER.Movie_Actor (
movie_id INT,
actor_id INT,
PRIMARY KEY (movie_id, actor_id),
FOREIGN KEY (movie_id) REFERENCES ADB_USER.Movie(movie_id),
FOREIGN KEY (actor_id) REFERENCES ADB_USER.Actor(actor_id)
);
-- Create the GenAI credential
BEGIN
DBMS_CLOUD.create_credential(
credential_name => 'GENAI_CRED',
user_ocid => 'ocid1.user.oc1....',
tenancy_ocid => 'ocid1.tenancy.oc1....',
private_key => 'vZ6cO...',
fingerprint => '86:7d:...'
);
END;
/
-- Create a profile
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name =>'GENAI',
attributes =>'{"provider": "oci",
"credential_name": "GENAI_CRED",
"object_list": [{"owner": "ADB_USER",
"oci_compartment_id": "ocid1.compartment.oc1...."}]
}');
END;
/
EXEC DBMS_CLOUD_AI.set_profile('GENAI');
-- Run the API for single table
BEGIN
DBMS_CLOUD_AI.GENERATE_SYNTHETIC_DATA(
profile_name => 'GENAI',
object_name => 'Director',
owner_name => 'ADB_USER',
record_count => 5
);
END;
/
PL/SQL procedure successfully completed.
-- Query the table to see results
SQL> SELECT * FROM ADB_USER.Director;
DIRECTOR_ID NAME
----------- ----------------------------------------------------------------------------------------------------
1 John Smith
2 Emily Chen
3 Michael Brown
4 Sarah Taylor
5 David Lee
-- Or ask select ai to show the results
SQL> select ai how many directors are there;
NUMBER_OF_DIRECTORS
-------------------
5
Beispiel: Synthetische Daten für mehrere Tabellen generieren
Nachdem Sie das AI-Providerprofil erstellt und festgelegt haben, generieren Sie mit DBMS_CLOUD_AI.GENERATE_SYNTHETIC_DATA Daten für mehrere Tabellen. Sie können Select AI abfragen oder verwenden, um auf die Eingabeaufforderungen in natürlicher Sprache zu antworten.
BEGIN
DBMS_CLOUD_AI.GENERATE_SYNTHETIC_DATA(
profile_name => 'GENAI',
object_list => '[{"owner": "ADB_USER", "name": "Director","record_count":5},
{"owner": "ADB_USER", "name": "Movie_Actor","record_count":5},
{"owner": "ADB_USER", "name": "Actor","record_count":10},
{"owner": "ADB_USER", "name": "Movie","record_count":5,"user_prompt":"all movies released in 2009"}]'
);
END;
/
PL/SQL procedure successfully completed.
-- Query the table to see results
SQL> select * from ADB_USER.Movie;
MOVIE_ID TITLE RELEASE_D GENRE DIRECTOR_ID
---------- -------------------------------------------------------- --------- --------------------------------------------------------------- -----------
1 The Dark Knight 15-JUL-09 Action 8
2 Inglourious Basterds 21-AUG-09 War 3
3 Up in the Air 04-SEP-09 Drama 6
4 The Hangover 05-JUN-09 Comedy 1
5 District 9 14-AUG-09 Science Fiction 10
-- Or ask select ai to show the results
SQL> select ai how many actors are there;
Number of Actors
----------------
10Beispiel: Synthetische Daten mit Beispielzeilen generieren
Um den AI-Service beim Generieren synthetischer Daten zu unterstützen, können Sie vorhandene Datensätze zufällig aus einer Tabelle auswählen. Beispiel: Wenn Sie {"sample_rows": 5} zum Argument params hinzufügen, können Sie 5 Beispielzeilen aus einer Tabelle an den AI-Provider senden. In diesem Beispiel werden 10 zusätzliche Zeilen basierend auf den Beispielzeilen aus der Tabelle Transactions generiert.
BEGIN
DBMS_CLOUD_AI.GENERATE_SYNTHETIC_DATA(
profile_name => 'GENAI',
object_name => 'Transactions',
owner_name => 'ADB_USER',
record_count => 10,
params => '{"sample_rows":5}'
);
END;
/Beispiel: Synthetische Datengenerierung mit Benutzer-Prompts anpassen
Mit dem Argument user_prompt können Sie zusätzliche Regeln oder Anforderungen für die Datengenerierung angeben. Dies kann auf eine einzelne Tabelle oder als Teil des Arguments object_list für mehrere Tabellen angewendet werden. Beispiel: In den folgenden Aufrufen an DBMS_CLOUD_AI.GENERATE_SYNTHETIC_DATA weist der Prompt die KI an, synthetische Daten zu Filmen zu generieren, die 2009 veröffentlicht wurden.
-- Definition for the Movie table CREATE TABLE Movie
CREATE TABLE Movie (
movie_id INT PRIMARY KEY,
title VARCHAR(100),
release_date DATE,
genre VARCHAR(50),
director_id INT,
FOREIGN KEY (director_id) REFERENCES Director(director_id)
);
BEGIN
DBMS_CLOUD_AI.GENERATE_SYNTHETIC_DATA(
profile_name => 'GENAI',
object_name => 'Movie',
owner_name => 'ADB_USER',
record_count => 10,
user_prompt => 'all movies are released in 2009',
params => '{"sample_rows":5}'
);
END;
/
BEGIN
DBMS_CLOUD_AI.GENERATE_SYNTHETIC_DATA(
profile_name => 'GENAI',
object_list => '[{"owner": "ADB_USER", "name": "Director","record_count":5},
{"owner": "ADB_USER", "name": "Movie_Actor","record_count":5},
{"owner": "ADB_USER", "name": "Actor","record_count":10},
{"owner": "ADB_USER", "name": "Movie","record_count":5,"user_prompt":"all movies are released in 2009"}]'
);
END;
/Beispiel: Verbesserung der synthetischen Datenqualität durch Verwendung von Tabellenstatistiken
Wenn eine Tabelle Spaltenstatistiken enthält oder aus einer Datenbank geklont wird, die Metadaten enthält, kann Select AI diese Statistiken verwenden, um Daten zu generieren, die den ursprünglichen Daten ähnlich oder konsistent sind.
Bei NUMBER-Spalten bestimmen die hohen und niedrigen Werte aus den Statistiken den Wertebereich. Beispiel: Wenn die Spalte SALARY in der ursprünglichen Tabelle EMPLOYEES zwischen 1000 und 10000 liegt, liegen die synthetischen Daten für diese Spalte ebenfalls in diesem Bereich.
Bei Spalten mit eindeutigen Werten, wie einer STATE-Spalte mit den Werten CA, WA und TX, verwenden die synthetischen Daten diese spezifischen Werte. Sie können dieses Feature mit dem Parameter {"table_statistics": true/false} verwalten. Standardmäßig sind die Tabellenstatistiken aktiviert.
BEGIN
DBMS_CLOUD_AI.GENERATE_SYNTHETIC_DATA(
profile_name => 'GENAI',
object_name => 'Movie',
owner_name => 'ADB_USER',
record_count => 10,
user_prompt => 'all movies released in 2009',
params => '{"sample_rows":5,"table_statistics":true}'
);
END;
/Beispiel: Verwenden von Spaltenkommentaren zur Datengenerierung
Wenn Spaltenkommentare vorhanden sind, schließt Select AI diese automatisch ein, um zusätzliche Informationen für das LLM während der Datengenerierung bereitzustellen. Beispiel: Ein Kommentar zur Spalte Status in einer Transaktionstabelle kann zulässige Werte auflisten, wie successful, failed, pending, canceled und need manual check. Sie können auch Kommentare hinzufügen, um die Spalte näher zu erläutern und KI-Services genauere Anweisungen oder Hinweise zum Generieren genauer Daten zu geben. Kommentare sind standardmäßig deaktiviert. Weitere Details finden Sie unter Optionale Parameter.
-- Use comment on column
COMMENT ON COLUMN Transaction.status IS 'the value for state should either be ''successful'', ''failed'', ''pending'' or ''canceled''';
/
BEGIN
DBMS_CLOUD_AI.GENERATE_SYNTHETIC_DATA(
profile_name => 'GENAI',
object_name => 'employees',
owner_name => 'ADB_USER',
record_count => 10
params => '{"comments":true}'
);
END;
/Beispiel: Eindeutige Werte bei der Generierung synthetischer Daten festlegen
Bei der Generierung großer Mengen synthetischer Daten mit LLMs sind doppelte Werte wahrscheinlich. Um dies zu verhindern, richten Sie ein eindeutiges Constraint für die entsprechende Spalte ein. Dadurch wird sichergestellt, dass Select AI Zeilen mit doppelten Werten in der LLM-Antwort ignoriert. Um Werte für bestimmte Spalten einzuschränken, können Sie außerdem user_prompt verwenden oder Kommentare hinzufügen, um die zulässigen Werte anzugeben, wie z.B. die Begrenzung einer STATE-Spalte auf CA, WA und TX.
-- Use 'user_prompt'
BEGIN
DBMS_CLOUD_AI.GENERATE_SYNTHETIC_DATA(
profile_name => 'GENAI',
object_name => 'employees',
owner_name => 'ADB_USER',
user_prompt => 'the value for state should either be CA, WA, or TX',
record_count => 10
);
END;
/
-- Use comment on column
COMMENT ON COLUMN EMPLOYEES.state IS 'the value for state should either be CA, WA, or TX'
/Beispiel: Synthetische Datengenerierung durch parallele Verarbeitung verbessern
Um die Laufzeit zu reduzieren, teilt Select AI Aufgaben zur Generierung synthetischer Daten in kleinere Blöcke für Tabellen ohne Primärschlüssel oder mit numerischen Primärschlüsseln auf. Diese Aufgaben werden parallel ausgeführt und interagieren mit dem KI-Provider, um Daten effizienter zu generieren. Der Parallelitätsgrad (DOP) in Ihrer Datenbank, der von Ihrem Autonomous Database-Servicegrad und den ECPU- oder OCPU-Einstellungen beeinflusst wird, bestimmt die Anzahl der Datensätze für jeden Chunk-Prozess. Die parallele Ausführung von Aufgaben verbessert im Allgemeinen die Performance, insbesondere bei der Generierung großer Datenmengen in vielen Tabellen. Um die parallele Verarbeitung der Generierung synthetischer Daten zu verwalten, legen Sie priority als optionalen Parameter fest. Siehe Optionale Parameter.
Übergeordnetes Thema: Beispiele für die Verwendung von Select AI
Beispiel: Datenzugriff aktivieren oder deaktivieren
Dieses Beispiel veranschaulicht, wie Administratoren den Datenzugriff steuern und verhindern können, dass Select AI tatsächliche Schematabellen an LLM sendet.
Datenzugriff deaktivieren
Um den Zugriff auf Schematabellen einzuschränken, melden Sie sich als Administrator an, und führen Sie das folgende Verfahren aus.
EXEC DBMS_CLOUD_AI.DISABLE_DATA_ACCESS;
PL/SQL procedure successfully completed.
Deaktivieren von Datenzugriffslimits Wählen Sie die AI-Aktion narrate und die Generierung synthetischer Daten aus. Die Aktion narrate und die Generierung synthetischer Daten lösen einen Fehler aus.
Melden Sie sich als Datenbankbenutzer an, erstellen und konfigurieren Sie Ihr AI-Profil. Lesen Sie Voraussetzungen für die Auswahl von AI ausführen, um Ihr AI-Profil zu konfigurieren.
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name =>'DATA_ACCESS',
attributes =>'{"provider": "openai",
"credential_name": "OPENAI_CRED",
"object_list": [{"owner":"SH"}]
}');
END;
/
EXEC DBMS_CLOUD_AI.SET_PROFILE('DATA_ACCESS');
select ai how many customers;
NUM_CUSTOMERS
55500
select ai narrate what are the top 3 customers in San Francisco;
ORA-20000: Data access is disabled for SELECT AI.
ORA-06512: at "C##CLOUD$SERVICE.DBMS_CLOUD", line 2228
ORA-06512: at "C##CLOUD$SERVICE.DBMS_CLOUD_AI", line 13157
ORA-06512: at line 1 https://docs.oracle.com/error-help/db/ora-20000/
The stored procedure 'raise_application_error' was called which causes this error to be generated
Error at Line: 1 Column: 6Das folgende Beispiel zeigt die Fehler, die ausgelöst werden, wenn Sie versuchen, synthetische Daten zu generieren.
BEGIN
DBMS_CLOUD_AI.GENERATE_SYNTHETIC_DATA(
profile_name => 'DATA_ACCESS_SDG',
object_name => 'CUSTOMERS_NEW',
owner_name => 'ADB_USER,
record_count => 5
);
END;
/
ERROR at line 1:
ORA-20000: Data access is disabled for SELECT AI.
ORA-06512: at "C##CLOUD$SERVICE.DBMS_CLOUD", line 2228
ORA-06512: at "C##CLOUD$SERVICE.DBMS_CLOUD_AI", line 13401
ORA-06512: at line 2Datenzugriff aktivieren
Das folgende Beispiel zeigt die Aktivierung des Datenzugriffs. Melden Sie sich als Administrator an, und führen Sie die folgenden Schritte aus:
EXEC DBMS_CLOUD_AI.ENABLE_DATA_ACCESS;
PL/SQL procedure successfully completed.Melden Sie sich als Datenbankbenutzer an, erstellen und konfigurieren Sie Ihr AI-Profil. Lesen Sie Voraussetzungen für die Auswahl von AI ausführen, um Ihr AI-Profil zu konfigurieren. Führen Sie die Aktion narrate aus, und generieren Sie synthetische Daten separat.
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name =>'DATA_ACCESS_NEW',
attributes =>'{"provider": "openai",
"credential_name": "OPENAI_CRED",
"object_list": [{"owner":"SH"}]
}');
END;
/
PL/SQL procedure successfully completed.
EXEC DBMS_CLOUD_AI.SET_PROFILE('DATA_ACCESS_NEW');
PL/SQL procedure successfully completed.
select ai how many customers;
NUM_CUSTOMERS
55500
select ai narrate what are the top 3 customers in San Francisco;
"RESPONSE"
"The top 3 customers in San Francisco are Cody Seto, Lauren Yaskovich, and Ian Mc"
Das folgende Beispiel zeigt eine erfolgreiche Generierung synthetischer Daten nach Aktivierung des Datenzugriffs.
BEGIN
DBMS_CLOUD_AI.GENERATE_SYNTHETIC_DATA(
profile_name => 'DATA_ACCESS_SDG',
object_name => 'CUSTOMERS_NEW',
owner_name => 'ADB_USER',
record_count => 5
);
END;
/
PL/SQL procedure successfully completed.Übergeordnetes Thema: Beispiele für die Verwendung von Select AI
Beispiel: Tabellenzugriff in AI-Profil einschränken
Dieses Beispiel zeigt, wie Sie den Tabellenzugriff einschränken und LLM anweisen, nur die in object_list des AI-Profils angegebenen Tabellen zu verwenden.
Setzen Sie enforce_object_list auf true, um den Tabellenzugriff auf das LLM einzuschränken.
Erstellen und konfigurieren Sie als Datenbankbenutzer Ihr AI-Profil. Lesen Sie Voraussetzungen für die Auswahl von AI ausführen, um Ihr AI-Profil zu konfigurieren.
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name =>'GOOGLE_ENFORCED',
attributes =>'{"provider": "google",
"credential_name": "GOOGLE_CRED",
"object_list": [{"owner": "ADB_USER", "name": "GENRE"},
{"owner": "ADB_USER", "name": "CUSTOMER"},
{"owner": "ADB_USER", "name": "PIZZA_SHOP"},
{"owner": "ADB_USER", "name": "STREAMS"},
{"owner": "ADB_USER", "name": "MOVIES"},
{"owner": "ADB_USER", "name": "ACTIONS"}],
"enforce_object_list" : "true"
}');
END;
/
PL/SQL procedure successfully completed.
EXEC DBMS_CLOUD_AI.set_profile('GOOGLE_ENFORCED');
PL/SQL procedure successfully completed.
select ai showsql please list the user tables;
RESPONSE
--------------------------------------------------------------------------------------------
SELECT 'ADB_USER.GENRE' AS TABLE_NAME FROM DUAL UNION ALL SELECT 'ADB_USER.CUSTOMER' AS
TABLE_NAME FROM DUAL UNION ALL SELECT 'ADB_USER.PIZZA_SHOP' AS TABLE_NAME FROM DUAL UNION
ALL SELECT 'ADB_USER.STREAMS' AS TABLE_NAME FROM DUAL UNION ALL SELECT 'ADB_USER.MOVIES'
AS TABLE_NAME FROM DUAL
--Wenn Sie enforce_object_list auf false setzen, wird LLM angewiesen, andere Tabellen und Views basierend auf seinen Vorkenntnissen zu verwenden.
BEGIN
DBMS_CLOUD_AI.CREATE_PROFILE(
profile_name =>'GOOGLE_ENFORCED1',
attributes =>'{"provider": "google",
"credential_name": "GOOGLE_CRED",
"object_list": [{"owner": "ADB_USER", "name": "GENRE"},
{"owner": "ADB_USER", "name": "CUSTOMER"},
{"owner": "ADB_USER", "name": "PIZZA_SHOP"},
{"owner": "ADB_USER", "name": "STREAMS"},
{"owner": "ADB_USER", "name": "MOVIES"},
{"owner": "ADB_USER", "name": "ACTIONS"}],
"enforce_object_list" : "false"
}');
END;
/
PL/SQL procedure successfully completed.
EXEC DBMS_CLOUD_AI.set_profile('GOOGLE_ENFORCED1');
PL/SQL procedure successfully completed.
select ai showsql please list the user tables;
RESPONSE
----------------------------------
SELECT TABLE_NAME FROM USER_TABLES
Übergeordnetes Thema: Beispiele für die Verwendung von Select AI
Beispiel: Groß-/Kleinschreibung für Spalten angeben
In diesem Beispiel wird gezeigt, wie Sie die Groß-/Kleinschreibung für Spalten im AI-Profil festlegen können.
Setzen Sie case_sensitive_values auf false, um Abfragen abzurufen, bei denen die Groß-/Kleinschreibung nicht beachtet wird.
Erstellen und konfigurieren Sie als Datenbankbenutzer Ihr AI-Profil. Lesen Sie Voraussetzungen für die Auswahl von AI ausführen, um Ihr AI-Profil zu konfigurieren.
BEGIN
DBMS_CLOUD_AI.create_profile(
profile_name =>'GOOGLE',
attributes =>'{"provider": "google",
"credential_name": "GOOGLE_CRED",
"object_list": [{"owner": "ADB_USER", "name": "GENRE"},
{"owner": "ADB_USER", "name": "CUSTOMER"},
{"owner": "ADB_USER", "name": "PIZZA_SHOP"},
{"owner": "ADB_USER", "name": "STREAMS"},
{"owner": "ADB_USER", "name": "MOVIES"},
{"owner": "ADB_USER", "name": "ACTIONS"}],
"case_sensitive_values" : "false"
}');
END;
/
PL/SQL procedure successfully completed.
-- With "case_sensitive_values" set to "false", LLM will give back case insensitive query.
select ai showsql how many people watch Inception;
RESPONSE
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
SELECT COUNT(DISTINCT c.CUSTOMER_ID) AS "COUNT"
FROM "ADB_USER"."CUSTOMER" c
JOIN "ADB_USER"."STREAMS" s ON c.CUSTOMER_ID = s.CUSTOMER_ID
JOIN "ADB_USER"."MOVIES" m ON s.MOVIE_ID = m.MOVIE_ID
WHERE UPPER(m.TITLE) = UPPER('Inception')Sie können eine Abfrage mit Beachtung der Groß-/Kleinschreibung mit doppelten Anführungszeichen angeben, obwohl case_sensitive_values auf false gesetzt ist.
select ai showsql how many people watch "Inception";
RESPONSE
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
SELECT COUNT(DISTINCT c.CUSTOMER_ID) AS "COUNT"
FROM "ADB_USER"."CUSTOMER" c JOIN "ADB_USER"."STREAMS" s ON
c.CUSTOMER_ID = s.CUSTOMER_ID JOIN "ADB_USER"."MOVIES" m ON
s.MOVIE_ID = m.MOVIE_ID WHERE m.TITLE = 'Inception'
Übergeordnetes Thema: Beispiele für die Verwendung von Select AI